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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and statistical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical notation and probability/statistics terms

    np_acts-logits-general · gemini-2.0-flash

    random variables convergence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Virtual
    -0.46
     Polo
    -0.46
     Tro
    -0.44
     roupa
    -0.43
    uertos
    -0.43
    plom
    -0.42
    GetAxis
    -0.42
    Carriera
    -0.42
    ف
    -0.42
     Stewart
    -0.42
    POSITIVE LOGITS
     random
    0.82
     randomness
    0.79
     betweenstory
    0.74
     probabilistic
    0.73
     Bayes
    0.71
     stochastic
    0.71
     Random
    0.70
    Попис
    0.70
     RANDOM
    0.69
    random
    0.69
    Act Density 3.999%

    No Known Activations