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

    Neuronpedia

    INDEX
    Explanations

    technical system components and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dir
    0.53
     SUBSCRIBE
    0.51
    ม
    0.50
     рады
    0.49
    ઈ
    0.48
    down
    0.46
    et
    0.45
    rhe
    0.45
    HR
    0.45
     History
    0.44
    POSITIVE LOGITS
     evaluaciones
    0.55
    ަރ
    0.50
     recipro
    0.47
     interesses
    0.47
     unid
    0.47
    胝
    0.46
     analyzers
    0.46
    ަ
    0.45
     cortes
    0.45
    ا
    0.45
    Act Density 0.001%

    No Known Activations