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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or statistics

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

    ranges or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.48
    RegressionTest
    -0.41
    baiki
    -0.39
    tahankan
    -0.38
    alignSelf
    -0.38
    Statistiche
    -0.37
    ArrowToggle
    -0.35
     zasad
    -0.34
    BufferException
    -0.34
    AndroidJUnit
    -0.33
    POSITIVE LOGITS
     afternoon
    0.67
    afternoon
    0.63
    noon
    0.63
    ConstraintMaker
    0.56
    AnchorStyles
    0.56
     evening
    0.55
    存于互联网档案馆
    0.53
     noon
    0.53
    Afternoon
    0.53
     hours
    0.52
    Act Density 0.000%

    No Known Activations