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

    Neuronpedia

    INDEX
    Explanations

    Layer Width

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jika
    0.86
    Altri
    0.76
     неза
    0.73
     altri
    0.72
    ("**
    0.71
    fär
    0.71
    प्र
    0.69
    Otros
    0.69
     autres
    0.68
    ');//
    0.68
    POSITIVE LOGITS
    acuse
    0.73
    have
    0.72
     slag
    0.72
     UFO
    0.70
     avi
    0.68
     semblance
    0.68
     Thee
    0.67
     তাহারা
    0.67
     mockery
    0.67
     sc
    0.66
    Act Density 0.001%

    No Known Activations