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

    Neuronpedia

    INDEX
    Explanations

    mini-pack extract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     allowances
    0.63
    کھ
    0.60
    Play
    0.55
     답
    0.54
    ยว
    0.53
     indiscriminate
    0.53
     aboard
    0.52
     Allowance
    0.52
     maiden
    0.52
    પુ
    0.52
    POSITIVE LOGITS
     मिन
    0.72
     diminishes
    0.71
    Extract
    0.71
     Pack
    0.70
     Extracts
    0.69
     माइक्रोस
    0.69
     ಪ್ಯಾ
    0.69
     pack
    0.67
    extract
    0.67
    迷你
    0.67
    Act Density 0.000%

    No Known Activations