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

    Neuronpedia

    INDEX
    Explanations

    highly contrasting evaluations of situations or outcomes

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

    bound and evaluation phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.56
    ckså
    -0.50
    ConverterFactory
    -0.50
     AttributeSet
    -0.48
     HasFactory
    -0.48
    IntoConstraints
    -0.48
    ParallelGroup
    -0.48
     createSlice
    -0.47
    berdayakan
    -0.46
     CommonModule
    -0.46
    POSITIVE LOGITS
    šinou
    0.44
    RegressionTest
    0.42
     worst
    0.40
     minimally
    0.40
     least
    0.39
    snprintf
    0.38
     Worst
    0.38
    OrNil
    0.38
    fgets
    0.36
    Misty
    0.36
    Act Density 0.014%

    No Known Activations