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

    Neuronpedia

    INDEX
    Explanations

    life events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Candidate
    -0.07
     своем
    -0.07
     seguir
    -0.07
     industry
    -0.07
     officer
    -0.07
    村民们
    -0.07
     Lisa
    -0.07
    builder
    -0.07
    藤
    -0.07
    ossier
    -0.07
    POSITIVE LOGITS
    _COLORS
    0.07
    �
    0.07
    เยอะ
    0.07
    孖
    0.07
     FLT
    0.07
    的到来
    0.06
     starred
    0.06
    忮
    0.06
     PRINT
    0.06
    矣
    0.06
    Act Density 0.063%

    No Known Activations