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

    Neuronpedia

    INDEX
    Explanations

    handling and affinity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合併
    0.52
    क
    0.51
     multimedia
    0.46
    サウンド
    0.45
     бри
    0.45
    тың
    0.45
    の
    0.45
    Multimedia
    0.44
    の種類
    0.44
     relazioni
    0.43
    POSITIVE LOGITS
    ignment
    0.44
     Derecho
    0.43
     etre
    0.43
     मील
    0.42
     Medicine
    0.42
     몰
    0.41
    useum
    0.40
     Acid
    0.40
    峄
    0.40
     Bull
    0.40
    Act Density 0.012%

    No Known Activations