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

    Neuronpedia

    INDEX
    Explanations

    checking and proving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ನಾಗ
    0.84
    岔
    0.84
    混合
    0.77
    骂
    0.74
     dictionary
    0.73
     读取
    0.73
    ไซ
    0.72
     Dictionary
    0.71
     Scribner
    0.70
     त्रिपाठी
    0.70
    POSITIVE LOGITS
     proof
    2.24
     evidence
    2.19
     Proof
    2.17
     Evidence
    2.10
    Proof
    2.04
     доказа
    2.02
     bukti
    2.01
    Evidence
    1.97
     preuves
    1.94
     prove
    1.92
    Act Density 0.592%

    No Known Activations