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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    commands
    -0.08
    _inc
    -0.07
    GROUP
    -0.07
     Bosch
    -0.07
     Explorer
    -0.07
    _cfg
    -0.06
    _colors
    -0.06
    =E
    -0.06
     proč
    -0.06
     hå
    -0.06
    POSITIVE LOGITS
     breakfast
    0.06
     гал
    0.06
     gal
    0.06
    リング
    0.06
    تبال
    0.06
    .parametrize
    0.06
    ель
    0.05
     時
    0.05
    .XRLabel
    0.05
    ahead
    0.05
    Act Density 0.023%

    No Known Activations