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

    Neuronpedia

    INDEX
    Explanations

    body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ac
    0.78
    EZ
    0.77
    Luego
    0.77
    sam
    0.77
    ‍
    0.75
    Υ
    0.75
    Muy
    0.74
     Фа
    0.73
     puro
    0.73
     घ
    0.71
    POSITIVE LOGITS
    ные
    1.12
    жная
    1.10
     አይነት
    1.05
    هاي
    1.03
    eseen
    0.95
    ش
    0.94
    ração
    0.94
    ercase
    0.91
     história
    0.91
    лены
    0.91
    Act Density 0.000%

    No Known Activations