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

    Neuronpedia

    INDEX
    Explanations

    numerical values and counts related to management and decision-making contexts

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

    Mathematical/scientific expressions

    np_acts-logits-general · gemini-2.0-flash

    legal citations and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "):
    -1.26
    ')):
    -1.14
    "],
    -1.08
    $",
    -1.05
    "];
    -1.04
    '):
    -1.02
    ")));
    -1.01
    "])
    -1.01
    '],
    -1.01
    `,
    -1.01
    POSITIVE LOGITS
     itſelf
    1.21
     Monfieur
    1.20
     poffible
    1.17
     Diſ
    1.15
     Reſ
    1.15
     Shakspeare
    1.14
     greateſt
    1.13
     myſelf
    1.13
     Anſ
    1.10
     Shaksp
    1.10
    Act Density 0.889%

    No Known Activations