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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     developers
    -0.08
     الجديدة
    -0.07
    岛国
    -0.07
     Estate
    -0.07
    িতা
    -0.07
     hela
    -0.07
    caps
    -0.07
     Villas
    -0.07
     Graves
    -0.07
     entertainer
    -0.07
    POSITIVE LOGITS
     предыдущ
    0.11
     previous
    0.10
    Previous
    0.10
    (previous
    0.09
    .previous
    0.09
    _previous
    0.09
     preth
    0.09
     vorige
    0.08
    previous
    0.08
     tidigare
    0.08
    Act Density 0.036%

    No Known Activations