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

    Neuronpedia

    INDEX
    Explanations

    code structure and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.84
     jika
    0.77
     ketika
    0.70
     när
    0.70
     is
    0.68
     rocking
    0.67
     handy
    0.66
     soccer
    0.66
     heightened
    0.66
     gets
    0.65
    POSITIVE LOGITS
    ק
    1.02
    f
    0.92
    failures
    0.82
    ک
    0.79
    క్
    0.79
    britann
    0.77
    פ
    0.77
    ب
    0.77
    쐞
    0.75
    ap
    0.75
    Act Density 0.084%

    No Known Activations