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

    Neuronpedia

    INDEX
    Explanations

    angular frames, labeled probes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     musculaire
    0.50
    पटॉप
    0.48
     nél
    0.47
    下来的
    0.47
    রেক
    0.46
    ็
    0.46
    दुल
    0.46
     અધ
    0.45
     sondern
    0.44
    benzoimidazol
    0.44
    POSITIVE LOGITS
    f
    0.53
    স
    0.50
    She
    0.49
    $
    0.48
    gawa
    0.45
    Core
    0.44
    United
    0.43
    m
    0.42
    Cro
    0.42
     Almanya
    0.42
    Act Density 0.001%

    No Known Activations