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

    Neuronpedia

    INDEX
    Explanations

    references to a license and its terms

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

    See the License

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.50
    RegressionTest
    -0.49
    transQ
    -0.47
    migrationBuilder
    -0.46
    
    -0.45
     GenerationType
    -0.44
     ModelExpression
    -0.44
    はじめに
    -0.44
     beginnetje
    -0.44
    endphp
    -0.44
    POSITIVE LOGITS
     See
    0.79
    See
    0.77
     see
    0.73
    see
    0.66
     Siehe
    0.66
     SEE
    0.57
     Sees
    0.55
    SEE
    0.54
    Lihat
    0.53
     sees
    0.52
    Act Density 0.028%

    No Known Activations