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

    Neuronpedia

    INDEX
    Explanations

    transformation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okie
    -0.06
    quite
    -0.06
    kok
    -0.06
    脂
    -0.06
     coron
    -0.06
     نسمة
    -0.06
     ArgumentException
    -0.05
    designation
    -0.05
    طلق
    -0.05
    ็น
    -0.05
    POSITIVE LOGITS
     ownership
    0.07
    .Pass
    0.07
     Pří
    0.07
     zwischen
    0.06
     hộ
    0.06
     twelve
    0.06
    Iter
    0.06
    -runtime
    0.06
    negative
    0.06
    -clean
    0.06
    Act Density 0.021%

    No Known Activations