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

    Neuronpedia

    INDEX
    Explanations

    information related to confirmation or verification status of claims or statements

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

    confirmation and refutation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argout
    -0.56
     """",
    -0.52
    modelBuilder
    -0.50
    ViewFeatures
    -0.50
    الحياه
    -0.49
    bkz
    -0.48
     StatefulWidget
    -0.46
    évaluateur
    -0.46
    consin
    -0.46
     late
    -0.46
    POSITIVE LOGITS
     offizielle
    0.42
     confirmation
    0.41
     oficjal
    0.39
    official
    0.38
     официаль
    0.37
    principalTable
    0.37
     bevestig
    0.36
    unconfirmed
    0.35
    confirmation
    0.35
     official
    0.34
    Act Density 0.025%

    No Known Activations