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

    Neuronpedia

    INDEX
    Explanations

    technical, medical, specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     değiş
    0.82
    ivities
    0.80
     lleno
    0.79
    étaient
    0.79
    ar
    0.78
    s
    0.74
    lovers
    0.73
    েও
    0.72
    pov
    0.72
    uities
    0.72
    POSITIVE LOGITS
    ज
    0.77
     Վ
    0.75
     Перейти
    0.73
    மை
    0.73
     Beim
    0.71
    ई
    0.71
     Bavarian
    0.71
     Ellington
    0.70
    क
    0.70
    і
    0.68
    Act Density 0.000%

    No Known Activations