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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ts
    -0.07
    驗
    -0.06
    ilst
    -0.06
    міністра
    -0.06
     SOUTH
    -0.06
    tap
    -0.06
    _os
    -0.06
    -ts
    -0.06
    ौं
    -0.06
    roulette
    -0.06
    POSITIVE LOGITS
    Debug
    0.08
     programs
    0.06
     WD
    0.06
     catching
    0.06
    /gcc
    0.06
    ↵    ↵
    0.06
    Regression
    0.06
    _FAILED
    0.06
     Lauren
    0.06
    重
    0.06
    Act Density 0.597%

    No Known Activations