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

    Neuronpedia

    INDEX
    Explanations

    terms of frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    近づ
    0.49
    ट्रोल
    0.48
    чиго
    0.48
    हुआ
    0.47
    主に
    0.45
    Æ
    0.45
     LOSS
    0.44
     могу
    0.44
     uglify
    0.44
    LOST
    0.43
    POSITIVE LOGITS
     (
    0.53
     frecuencia
    0.44
    (
    0.43
     frequência
    0.43
     või
    0.43
     fréqu
    0.42
     oder
    0.42
     fréquente
    0.41
     Accent
    0.40
     na
    0.40
    Act Density 0.003%

    No Known Activations