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

    Neuronpedia

    INDEX
    Explanations

    symbols or syntax related to command-line interface operations

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

    command line arguments and flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.54
    GraphicsUnit
    -0.49
    antaranya
    -0.45
    parsedMessage
    -0.43
    
    -0.43
    featureID
    -0.41
    ArgsConstructor
    -0.40
     bây
    -0.40
    VersionUID
    -0.40
     Italij
    -0.40
    POSITIVE LOGITS
    ('--
    1.00
    ("--
    0.93
     "--
    0.93
     '--
    0.92
     --
    0.92
    (--
    0.80
     (--
    0.73
    '--
    0.72
    #--
    0.71
     lenker
    0.71
    Act Density 0.016%

    No Known Activations