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

    Neuronpedia

    INDEX
    Explanations

    grammatical corrections, advice, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizing
    0.46
     signal
    0.45
    it
    0.45
     knack
    0.45
     vending
    0.45
    '
    0.45
     son
    0.44
    is
    0.44
     remediation
    0.44
     mode
    0.43
    POSITIVE LOGITS
    鍱
    0.52
    ✕
    0.52
    墘
    0.51
    <unused2125>
    0.50
    இந்திய
    0.49
    ಗೊಳ್ಳ
    0.49
    刄
    0.49
    ünüz
    0.49
    大きな
    0.49
    ﾐ
    0.49
    Act Density 0.003%

    No Known Activations