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

    Neuronpedia

    INDEX
    Explanations

    words indicating frequency or commonality in various contexts

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

    about commonness or frequency

    np_acts-logits-general · gemini-2.0-flash

    frequency and commonality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.79
     GenerationType
    -0.71
     مرئيه
    -0.67
     '\\;'
    -0.62
    ViewFeatures
    -0.59
     ModelExpression
    -0.58
    󠁣
    -0.57
    IntoConstraints
    -0.56
     виправивши
    -0.56
     MenuView
    -0.54
    POSITIVE LOGITS
     occurrence
    0.75
     frequent
    0.68
     occurrences
    0.68
     frequency
    0.61
     fréquence
    0.60
     frequently
    0.59
     frecu
    0.56
     frequência
    0.56
     Occurrence
    0.55
     frecuentes
    0.54
    Act Density 0.523%

    No Known Activations