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

    Neuronpedia

    INDEX
    Explanations

    Organizations and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یں
    1.84
    を含む
    1.66
    tones
    1.52
    きます
    1.44
    امه
    1.43
    เป็น
    1.41
    ご
    1.41
    前辈
    1.37
     semblance
    1.36
    δήποτε
    1.36
    POSITIVE LOGITS
    a
    1.88
    OS
    1.63
    GIN
    1.63
    ä
    1.61
    That
    1.57
    playlists
    1.56
    т
    1.56
     Britannica
    1.55
    ट
    1.55
    UNESCO
    1.54
    Act Density 0.058%

    No Known Activations