Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Personal expressions

    np_max-act · gemini-2.0-flash

    The neuron fires on words and short sequences that intensify or heighten emotional/erotic excitement (e.g. adverbs and verbs in phrases like “thought of it was driving me wild,” “makes it even more exciting”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     coastal
    -0.07
     AppConfig
    -0.07
    <Transaction
    -0.07
    Err
    -0.06
     Yo
    -0.06
     UIView
    -0.06
    -Am
    -0.06
     Datagram
    -0.06
    _SEC
    -0.06
    -prop
    -0.06
    POSITIVE LOGITS
    ednou
    0.07
     ",");↵
    0.07
    ogie
    0.07
    /')↵
    0.07
    导
    0.06
    _AXIS
    0.06
    invite
    0.06
     ****************************************************************
    0.06
     aktiv
    0.06
     steam
    0.06
    Act Density 0.063%

    No Known Activations