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

    Neuronpedia

    INDEX
    Explanations

    ой

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sharper
    -0.07
     construction
    -0.07
    主任
    -0.06
    .cost
    -0.06
     güvenli
    -0.06
     validators
    -0.06
    Parm
    -0.06
     saldırı
    -0.06
    755
    -0.06
    .Graphics
    -0.06
    POSITIVE LOGITS
    _MAJOR
    0.08
    !",
    0.07
    ayah
    0.07
     دریا
    0.06
    ==
    0.06
    /js
    0.06
    ero
    0.06
     občan
    0.06
    /process
    0.06
    ↵                ↵
    0.06
    Act Density 0.234%

    No Known Activations