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

    Neuronpedia

    INDEX
    Explanations

    graph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.87
     weighed
    -0.81
    graph
    -0.78
     Wikimedijinoj
    -0.73
    httphttps
    -0.68
     виправивши
    -0.66
    igshid
    -0.64
    LookAnd
    -0.62
     BoxFit
    -0.62
    beat
    -0.61
    POSITIVE LOGITS
    Bibliografia
    0.51
     Emer
    0.47
    assertRaises
    0.46
    zzini
    0.45
    TIA
    0.43
    ])).
    0.43
    erba
    0.43
     Proud
    0.42
    Sortie
    0.42
    Liens
    0.41
    Act Density 0.010%

    No Known Activations