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

    Neuronpedia

    INDEX
    Explanations

    prices demand startups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ។
    0.49
     adhipp
    0.45
    paragus
    0.44
     cáps
    0.42
    hundred
    0.42
    喜剧
    0.42
     اعزائي
    0.41
    getImageFolder
    0.41
    ෆ
    0.41
    キャップ
    0.40
    POSITIVE LOGITS
     wish
    0.46
     trend
    0.45
     evolve
    0.45
     BMC
    0.45
     એન
    0.44
     परंपरागत
    0.43
     evolucion
    0.42
     change
    0.40
    こうした
    0.40
    …,
    0.40
    Act Density 0.003%

    No Known Activations