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

    Neuronpedia

    INDEX
    Explanations

    failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    잖
    -0.07
    aths
    -0.06
    meyen
    -0.06
    mom
    -0.06
    Hist
    -0.06
    耀
    -0.06
    abble
    -0.06
    icontrol
    -0.06
    ратно
    -0.06
    ARP
    -0.06
    POSITIVE LOGITS
     citizenship
    0.07
     سف
    0.07
    -tests
    0.07
    123
    0.06
     أخ
    0.06
     canada
    0.06
    entials
    0.06
    포츠
    0.06
    ÷
    0.06
    limitations
    0.06
    Act Density 0.029%

    No Known Activations