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

    Neuronpedia

    INDEX
    Explanations

    /she

    np_max-act · gemini-2.0-flash

    The neuron is keyed to occurrences of the “he/she” pronoun form (the slash‐separated gendered pronoun).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Roc
    -0.06
     sunt
    -0.06
    EmptyEntries
    -0.06
    acid
    -0.06
    ENCHMARK
    -0.06
    Cold
    -0.06
     이야
    -0.06
     sweetness
    -0.06
    <N
    -0.06
     explanatory
    -0.06
    POSITIVE LOGITS
    lesia
    0.08
    IRM
    0.07
     grupo
    0.06
     markers
    0.06
    LES
    0.06
     gồm
    0.06
     erotik
    0.06
     Admir
    0.06
     moz
    0.06
    _Def
    0.06
    Act Density 0.002%

    No Known Activations