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

    Neuronpedia

    INDEX
    Explanations

    Ac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +n
    -0.06
     �
    -0.06
    �
    -0.06
     persu
    -0.06
    -eslint
    -0.06
     Tie
    -0.06
     Pirate
    -0.06
     rumors
    -0.06
     Residence
    -0.06
     Calories
    -0.06
    POSITIVE LOGITS
    .ax
    0.07
    _CATEGORY
    0.06
    COPY
    0.06
    ораль
    0.06
    immutable
    0.06
    ảnh
    0.06
     dış
    0.06
     Interrupt
    0.06
    535
    0.06
     Brit
    0.06
    Act Density 0.414%

    No Known Activations