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

    Neuronpedia

    INDEX
    Explanations

    names and familial relationships in historical contexts

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

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Abitanti
    -0.42
     cleave
    -0.41
    djangoproject
    -0.40
     mania
    -0.38
    janos
    -0.38
     himo
    -0.36
     onPostExecute
    -0.36
     habit
    -0.36
     vra
    -0.35
     idio
    -0.35
    POSITIVE LOGITS
     nakalista
    0.46
     كومونز
    0.46
    Aiheesta
    0.45
    Transkript
    0.44
     وتسجيلات
    0.44
     dezelve
    0.42
    TokenNameRBRACE
    0.42
    Autoritní
    0.41
    رشف
    0.41
     CreateTagHelper
    0.41
    Act Density 0.002%

    No Known Activations