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

    Neuronpedia

    INDEX
    Explanations

    finding vs creating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ু
    0.48
    ു
    0.46
    शाली
    0.43
    했지만
    0.43
    트로
    0.42
    ි
    0.42
     troch
    0.42
    ილი
    0.41
    -}
    0.39
     الآن
    0.39
    POSITIVE LOGITS
     melhorar
    0.44
    Sports
    0.43
    DIR
    0.42
    ཧ
    0.41
     Logo
    0.41
     eliminar
    0.41
     Dir
    0.41
     eliminado
    0.41
     lohnt
    0.41
    Dir
    0.40
    Act Density 0.004%

    No Known Activations