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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting marks that signify structure within text

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

    after colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dabei
    -0.40
     acercar
    -0.37
     behind
    -0.36
     sozialen
    -0.35
     apunt
    -0.35
     detrás
    -0.35
    Tahun
    -0.35
     bañ
    -0.35
     czy
    -0.35
    Ciclo
    -0.34
    POSITIVE LOGITS
    setVerticalGroup
    1.12
    ViewFeatures
    0.86
    tagHelperRunner
    0.86
     للاسماء
    0.84
     الحره
    0.82
     kaarangay
    0.82
    SharedCtor
    0.81
     betweenstory
    0.79
    PerformLayout
    0.71
    Hentet
    0.69
    Act Density 0.011%

    No Known Activations