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

    Neuronpedia

    INDEX
    Explanations

    computer software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.75
     betweenstory
    -0.71
    ngOn
    -0.64
     Greeley
    -0.63
     colorés
    -0.63
     ledig
    -0.61
    もしれない
    -0.61
    exprimer
    -0.60
     camada
    -0.59
     konge
    -0.58
    POSITIVE LOGITS
    LEncoder
    0.54
    iNdEx
    0.50
    basicConfig
    0.49
    putExtra
    0.49
    mbggenerated
    0.48
     SafeMath
    0.48
     playback
    0.47
    bewerken
    0.47
    astify
    0.47
    stringify
    0.45
    Act Density 0.200%

    No Known Activations