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

    Neuronpedia

    INDEX
    Explanations

    why is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    го
    0.80
    トラブル
    0.74
    ੀਆਂ
    0.73
    「
    0.71
    、「
    0.71
    [\
    0.70
    🔩
    0.70
    🧵
    0.69
    データを
    0.69
    アリ
    0.69
    POSITIVE LOGITS
    days
    0.80
    biotic
    0.80
    nahi
    0.75
     methylated
    0.73
     vorticity
    0.73
    nikiem
    0.72
    diphenyl
    0.72
     ولو
    0.71
    ูณ
    0.71
     diploid
    0.71
    Act Density 0.000%

    No Known Activations