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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal reflection and critique

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

    biased or prejudicial effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linkovi
    -0.48
     Numerade
    -0.48
     GenerationType
    -0.48
    UrlResolution
    -0.40
    reuth
    -0.40
    Fors
    -0.39
     feroit
    -0.39
     ľud
    -0.39
     مرئيه
    -0.38
     estud
    -0.38
    POSITIVE LOGITS
    WithIOException
    0.45
     ब्रेकडाउन
    0.44
     kasarigan
    0.41
     bic
    0.38
     involu
    0.38
    ükemmel
    0.37
    InitVars
    0.36
    nestjs
    0.36
     onBind
    0.35
    Välislingid
    0.35
    Act Density 0.066%

    No Known Activations