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

    Neuronpedia

    INDEX
    Explanations

    AD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аних
    -0.07
     slept
    -0.07
     blunt
    -0.06
    oth
    -0.06
    érer
    -0.06
     onTouch
    -0.06
    -expand
    -0.06
     meant
    -0.06
     horrors
    -0.06
     erroneous
    -0.06
    POSITIVE LOGITS
    _CAR
    0.07
     spor
    0.06
    ,ev
    0.06
     reklam
    0.06
    _executor
    0.06
     sr
    0.06
     Gand
    0.06
    _copy
    0.06
     categorical
    0.06
     hrom
    0.06
    Act Density 0.035%

    No Known Activations