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

    Neuronpedia

    INDEX
    Explanations

    php code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    こと
    1.16
    𝐠
    0.95
    Из
    0.94
    tedir
    0.88
    s
    0.85
     ไม่
    0.84
    gg
    0.83
    tes
    0.82
     위한
    0.81
    에서
    0.81
    POSITIVE LOGITS
    urt
    0.94
    is
    0.93
    ী
    0.85
    PACT
    0.83
     buts
    0.82
    PATHS
    0.82
    isements
    0.81
    و
    0.80
    PER
    0.80
    ènes
    0.80
    Act Density 0.000%

    No Known Activations