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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卻
    -0.07
    mostly
    -0.07
     mostly
    -0.07
     неп
    -0.06
     probl
    -0.06
     coraz
    -0.06
    ]}"↵
    -0.06
     LPARAM
    -0.06
     نق
    -0.06
    else
    -0.06
    POSITIVE LOGITS
    -translate
    0.07
    aban
    0.06
     fab
    0.06
     Mohammed
    0.06
     Kew
    0.06
    สะ
    0.06
    od
    0.06
     unemployed
    0.06
    arda
    0.06
    abo
    0.06
    Act Density 0.005%

    No Known Activations