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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and configurations related to programming or software components

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

    code identifiers and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.42
     utafitiHapana
    -0.40
     باخ
    -0.39
     للمعارف
    -0.38
    </tr>
    -0.38
     Spisak
    -0.37
    TokenNameLBRACE
    -0.36
    <h1>
    -0.35
    -0.35
    </tbody>
    -0.34
    POSITIVE LOGITS
    Bakgrunnsstoff
    0.60
    ništvo
    0.56
    \{\\
    0.52
     للاسماء
    0.49
     Chwiliwch
    0.49
     ويكيپيديا
    0.48
    windowFixed
    0.48
    andte
    0.47
     Wicidata
    0.47
    سطس
    0.47
    Act Density 0.146%
    No Known Activations