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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initial
    -0.09
     initially
    -0.09
    initial
    -0.08
    _initial
    -0.08
     immin
    -0.07
     मू
    -0.07
     originalmente
    -0.07
     aanv
    -0.07
    .initial
    -0.07
     malé
    -0.07
    POSITIVE LOGITS
     محف
    0.09
    untza
    0.08
     మంది
    0.08
    aucoup
    0.08
     Landschaft
    0.08
     nichts
    0.08
    的软件
    0.08
    etch
    0.08
    агог
    0.08
    Thirty
    0.08
    Act Density 0.000%

    No Known Activations