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

    Neuronpedia

    INDEX
    Explanations

    comparative statements related to values being below or above certain thresholds or averages

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

    a level compared to a standard

    np_acts-logits-general · gemini-2.0-flash

    values below normal or standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.73
     esternos
    -0.71
    -0.60
     kaarangay
    -0.60
    الإنجليزية
    -0.57
    vants
    -0.56
    出版年
    -0.54
    abestanden
    -0.53
    UnsafeEnabled
    -0.53
     OMIT
    -0.53
    POSITIVE LOGITS
     normal
    0.91
    normal
    0.75
     what
    0.74
     optimal
    0.74
     par
    0.72
     expectations
    0.71
     normale
    0.71
     desired
    0.69
     target
    0.67
     standard
    0.66
    Act Density 0.466%

    No Known Activations