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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions or references to percentages and proportions

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

    quantifying proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.40
     beginnetje
    -0.35
     CanadaChoose
    -0.34
    ueuse
    -0.33
    THRESH
    -0.31
    -0.31
    @[+][
    -0.31
     Wunsch
    -0.29
     độ
    -0.29
    °
    -0.29
    POSITIVE LOGITS
    Часть
    0.61
    WaitGroup
    0.59
    Majority
    0.55
    ↹
    0.53
    $_['
    0.51
     majority
    0.50
     Majority
    0.49
    FieldNumber
    0.48
    ɵɵelementEnd
    0.47
    Few
    0.47
    Act Density 0.374%

    No Known Activations