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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prer
    -0.07
     alo
    -0.07
    BEST
    -0.06
    ''''
    -0.06
    �
    -0.06
    >()
    -0.06
    CMD
    -0.06
    indexOf
    -0.06
    _detalle
    -0.06
    %'↵
    -0.06
    POSITIVE LOGITS
    Humans
    0.06
     Brewers
    0.06
     stranger
    0.06
    apsulation
    0.06
     cams
    0.06
    sizlik
    0.06
    โม
    0.06
    dae
    0.06
     advertis
    0.06
    .integer
    0.06
    Act Density 0.036%

    No Known Activations