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

    Neuronpedia

    INDEX
    Explanations

    python imports libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     یا
    0.71
    achusetts
    0.66
    BleStatus
    0.66
     αλλά
    0.66
    ্ী
    0.64
    รรม
    0.64
     هذا
    0.63
    がなく
    0.63
     nhưng
    0.63
    <unused405>
    0.63
    POSITIVE LOGITS
    l
    0.94
    n
    0.86
    ↵
    0.75
    id
    0.67
    in
    0.64
    ad
    0.63
    t
    0.61
    ↵↵↵
    0.60
     metal
    0.60
    ↵↵↵↵
    0.59
    Act Density 0.110%

    No Known Activations