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

    Neuronpedia

    INDEX
    Explanations

    Probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brain
    -0.08
     {};↵↵
    -0.08
    argc
    -0.08
     marching
    -0.08
     गर्द
    -0.08
    integer
    -0.08
    wind
    -0.07
    apped
    -0.07
    @Enable
    -0.07
    pag
    -0.07
    POSITIVE LOGITS
     probability
    0.12
     probabilities
    0.12
    Probability
    0.11
     Probability
    0.11
    概率
    0.10
    _probability
    0.09
     roulette
    0.09
    _prob
    0.09
     encounter
    0.09
    Selection
    0.08
    Act Density 0.055%

    No Known Activations