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

    Neuronpedia

    INDEX
    Explanations

    output JSON format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вання
    2.22
    न
    1.94
    ся
    1.77
    তে
    1.73
    tı
    1.71
    t
    1.70
    ến
    1.68
    /
    1.64
    ности
    1.64
    ность
    1.62
    POSITIVE LOGITS
     FS
    1.92
     причем
    1.84
     erreurs
    1.82
     deliciously
    1.81
    agę
    1.81
     arrhyth
    1.80
    pieceSelection
    1.78
     '$
    1.77
     depositphotos
    1.76
    ➠
    1.75
    Act Density 0.000%

    No Known Activations