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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions and discussions about reasoning

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

    Follows a statement needing further explanation

    np_acts-logits-general · gemini-2.0-flash

    explaining why or giving reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.60
    TestTools
    -0.60
    úgó
    -0.56
    argout
    -0.54
    jsonwebtoken
    -0.53
     useStyles
    -0.53
    parency
    -0.52
    évaluateur
    -0.52
    ⓘ
    -0.51
    COUVER
    -0.49
    POSITIVE LOGITS
     reason
    1.70
     because
    1.69
     reasons
    1.55
    because
    1.52
    理由は
    1.49
     perché
    1.47
    reason
    1.41
     Çünkü
    1.40
     why
    1.39
    なぜ
    1.39
    Act Density 0.461%

    No Known Activations