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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate a lack of clarity or specificity

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

    not specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.64
     endfor
    -0.63
    gså
    -0.48
    AddTagHelper
    -0.47
     للاسماء
    -0.46
    writerow
    -0.45
    neté
    -0.45
     onStop
    -0.44
     resourceCulture
    -0.44
    LayoutPanel
    -0.44
    POSITIVE LOGITS
     vague
    1.89
     vaguely
    1.41
     vagu
    1.16
     vagues
    1.02
     vaga
    0.96
    ague
    0.90
     ambiguous
    0.84
     hazy
    0.82
     faintly
    0.77
     faint
    0.77
    Act Density 0.010%

    No Known Activations