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

    Neuronpedia

    INDEX
    Explanations

    king or queen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -web
    -0.07
     webpack
    -0.06
     inside
    -0.06
     LLVM
    -0.06
    uffy
    -0.06
    iomanip
    -0.06
    News
    -0.06
     Radio
    -0.06
     jednak
    -0.06
    La
    -0.06
    POSITIVE LOGITS
    ulling
    0.06
    .createCell
    0.06
     samostat
    0.06
    TES
    0.06
    気に入
    0.06
     سایر
    0.06
    /t
    0.06
    apsed
    0.06
    .phase
    0.06
     Eylül
    0.06
    Act Density 0.011%

    No Known Activations