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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    116
    -0.07
     وأ
    -0.06
    (UINT
    -0.06
     쓰
    -0.06
     FULL
    -0.06
    ()+
    -0.06
    ysts
    -0.06
     doom
    -0.05
    循
    -0.05
    =@"
    -0.05
    POSITIVE LOGITS
    ),
    0.07
    ivals
    0.07
     perpetr
    0.07
     طلب
    0.06
    elin
    0.06
     představ
    0.06
     قول
    0.06
    Implemented
    0.06
     بانک
    0.06
    bourg
    0.06
    Act Density 0.030%

    No Known Activations