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

    Neuronpedia

    INDEX
    Explanations

    A followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    decyd
    0.53
    汅
    0.53
     gada
    0.53
    西亚
    0.53
     डिप्ट
    0.52
     तस्करी
    0.52
    ש
    0.52
    ുപത്രി
    0.52
    ગાહી
    0.51
    عرِّف
    0.50
    POSITIVE LOGITS
    _
    0.50
    S
    0.47
    ...
    0.46
     by
    0.46
     holds
    0.45
    -
    0.44
    U
    0.44
     Up
    0.43
     (
    0.42
    ?
    0.42
    Act Density 0.000%

    No Known Activations