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

    Neuronpedia

    INDEX
    Explanations

    -toggle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tripod
    -0.07
    evice
    -0.07
    :boolean
    -0.07
     omitted
    -0.07
    ARCHAR
    -0.06
    .Str
    -0.06
    Scene
    -0.06
     race
    -0.06
    UIFont
    -0.06
    .lab
    -0.06
    POSITIVE LOGITS
    戻
    0.06
     Grund
    0.06
     такими
    0.06
     jeden
    0.06
    ходим
    0.06
     Knights
    0.06
    (vertex
    0.06
    0.06
    ]",↵
    0.06
    bestos
    0.06
    Act Density 0.001%

    No Known Activations