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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ping
    -0.10
     аб
    -0.09
    noop
    -0.09
    seo
    -0.08
    itches
    -0.08
    cement
    -0.08
    PING
    -0.08
    🔥
    -0.08
    klan
    -0.08
     stimulation
    -0.08
    POSITIVE LOGITS
     probability
    0.21
    Probability
    0.19
     Probability
    0.19
     probabilities
    0.18
    概率
    0.17
    _probability
    0.17
    _prob
    0.13
     Wahrscheinlichkeit
    0.13
     Prob
    0.12
     вероятность
    0.12
    Act Density 0.057%

    No Known Activations