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

    Neuronpedia

    INDEX
    Explanations

    physical health, steps for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diarrhoea
    2.39
    せ
    2.22
    佢
    2.20
    ματο
    2.17
    効果
    2.17
    ungannya
    2.16
    ュー
    2.15
     amma
    2.14
    hoea
    2.09
    さに
    2.07
    POSITIVE LOGITS
    7
    2.14
    born
    2.01
    eland
    2.01
     Tengah
    1.95
    6
    1.95
    ísk
    1.94
     reclama
    1.94
     Selatan
    1.92
     terület
    1.91
     uninhab
    1.89
    Act Density 0.195%

    No Known Activations