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

    Neuronpedia

    INDEX
    Explanations

    insured

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    荪
    -0.07
    Legal
    -0.07
    קרה
    -0.07
     Fixture
    -0.07
    �
    -0.07
    лез
    -0.06
     cases
    -0.06
    arious
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    =%.
    0.07
    /*.
    0.07
     padding
    0.07
    积极推动
    0.07
     approx
    0.07
    ITH
    0.07
    难度
    0.07
    引用
    0.07
    号楼
    0.07
     urllib
    0.07
    Act Density 0.003%

    No Known Activations