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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating certainty or emphasis in opinions and statements

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

    emphasizing adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.40
    حوالہ
    -0.36
     متعلقه
    -0.35
    BindView
    -0.35
    Reason
    -0.34
    fritt
    -0.34
    lanzen
    -0.34
    reason
    -0.34
    pyr
    -0.33
    selig
    -0.33
    POSITIVE LOGITS
    IsMutable
    0.59
    دانشنامهٔ
    0.50
    getActiveSheet
    0.48
     незавершена
    0.46
    ScopeManager
    0.46
     فريبيس
    0.44
     CreateTagHelper
    0.43
     الرياضيه
    0.43
     AppCompatTheme
    0.42
    beros
    0.42
    Act Density 0.021%

    No Known Activations