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

    Neuronpedia

    INDEX
    Explanations

    platform services and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    1.16
    of
    0.99
    л
    0.98
    ية
    0.96
    يت
    0.95
    at
    0.91
    g
    0.90
    ِي
    0.88
    នៃ
    0.87
    .".
    0.87
    POSITIVE LOGITS
    '
    1.94
    ’
    1.64
    )
    1.38
    0
    1.30
    €™
    1.16
     platform
    1.15
    -
    1.13
     MOU
    1.07
     XGB
    1.06
    (
    1.06
    Act Density 0.028%

    No Known Activations