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

    Neuronpedia

    INDEX
    Explanations

    health points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    વી
    0.53
    ಷ್ಣ
    0.48
    ಣೆ
    0.48
    નની
    0.48
    ﺼ
    0.47
    جة
    0.47
     efectivos
    0.47
    ᱡ
    0.47
     marcas
    0.46
     ايجاد
    0.45
    POSITIVE LOGITS
    om
    0.59
     on
    0.53
    ü
    0.52
    em
    0.52
     that
    0.51
    ong
    0.50
    ak
    0.49
    า
    0.49
    ia
    0.48
    on
    0.48
    Act Density 0.003%

    No Known Activations