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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal involvement or feelings

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

    past tense verbs and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arraycopy
    -0.43
     Keim
    -0.41
    //
    -0.41
    routeProvider
    -0.39
    sequelize
    -0.38
    tagHelperRunner
    -0.38
     wikipagina
    -0.37
     juist
    -0.36
    IBAction
    -0.36
    ukunft
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.59
    LookAnd
    0.47
     myſelf
    0.44
    Zo
    0.43
     PPR
    0.42
     TSI
    0.41
    хьтан
    0.41
     Trad
    0.41
     Notebooks
    0.40
    Jeep
    0.40
    Act Density 0.340%

    No Known Activations