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

    Neuronpedia

    INDEX
    Explanations

    Week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ерам
    -0.08
    .infrastructure
    -0.08
    .func
    -0.07
    airs
    -0.07
     histories
    -0.07
    Pol
    -0.07
    .dr
    -0.07
    Arrays
    -0.07
    wer
    -0.07
    perti
    -0.07
    POSITIVE LOGITS
     Without
    0.09
    ("/",
    0.09
    (",",
    0.08
    <(),
    0.08
    ('.',
    0.08
     Livre
    0.08
     terci
    0.08
     Ln
    0.08
    (',',
    0.08
    ('',
    0.08
    Act Density 0.036%

    No Known Activations