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

    Neuronpedia

    INDEX
    Explanations

    detailed explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indestruct
    0.45
    નિક
    0.45
     peligros
    0.44
     பதில்
    0.44
     técnico
    0.44
    anjay
    0.43
     sheen
    0.43
    ござ
    0.42
     संलग्न
    0.42
    ሟ
    0.42
    POSITIVE LOGITS
    ,
    0.53
     as
    0.52
     after
    0.48
    RE
    0.47
     Stew
    0.45
    Earth
    0.45
    Ung
    0.45
     of
    0.44
    UN
    0.44
    Water
    0.44
    Act Density 0.001%

    No Known Activations