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

    Neuronpedia

    INDEX
    Explanations

    narrations

    np_max-act · gemini-2.0-flash

    The neuron fires on words and short phrases that express involuntary feelings or sensations (e.g. “couldn’t help but feel a sense of excitement/anticipation”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    blur
    -0.07
     acompan
    -0.07
    foobar
    -0.07
    کر
    -0.06
     principalColumn
    -0.06
    Because
    -0.06
    อนไลน
    -0.06
     misogyn
    -0.06
     возникает
    -0.06
     anomal
    -0.06
    POSITIVE LOGITS
     entertained
    0.06
    CLE
    0.06
    parated
    0.06
    .netty
    0.06
     Options
    0.06
     captures
    0.06
    رت
    0.06
     Aleks
    0.06
    (dict
    0.06
     dominate
    0.06
    Act Density 0.079%

    No Known Activations