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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    はじめに
    -0.57
    PreferredItem
    -0.56
    resave
    -0.56
    chism
    -0.47
    Tikang
    -0.47
    knex
    -0.46
    AnimationsModule
    -0.46
    aderno
    -0.45
    airobi
    -0.45
    ftagPool
    -0.44
    POSITIVE LOGITS
    ?...
    0.74
     ?...
    0.71
    ?<
    0.71
    لمانيا
    0.69
    !...
    0.68
    ?");
    0.68
    ?
    0.68
    !");
    0.66
    ?\\
    0.66
    ?}
    0.66
    Act Density 0.013%

    No Known Activations