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

    Neuronpedia

    INDEX
    Explanations

    override method declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    橑
    0.42
    تباط
    0.40
    那么
    0.39
    鐏
    0.39
    棪
    0.38
    ENSIVE
    0.38
    变换
    0.37
    流入
    0.37
    拿下
    0.37
    frau
    0.37
    POSITIVE LOGITS
     over
    1.17
    @
    1.07
     @
    1.05
     override
    1.02
     Over
    1.00
    override
    0.98
    over
    0.97
     overrides
    0.95
    Override
    0.94
     över
    0.94
    Act Density 0.004%

    No Known Activations