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

    Neuronpedia

    INDEX
    Explanations

    you/me pronouns

    np_max-act · gemini-2.0-flash

    This neuron flags occurrences of first-person pronouns (like “I,” “me,” “my,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hs
    -0.07
    hti
    -0.06
     lunches
    -0.06
    كيل
    -0.06
    -parts
    -0.06
    /Login
    -0.06
    -call
    -0.06
    .frame
    -0.06
     Ded
    -0.06
     écrit
    -0.06
    POSITIVE LOGITS
     ово
    0.07
    绿
    0.07
     handic
    0.06
    _svg
    0.06
     barr
    0.06
    ंध
    0.06
     WV
    0.06
    撤
    0.06
    Johnny
    0.06
     sourceMapping
    0.06
    Act Density 0.046%

    No Known Activations