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

    Neuronpedia

    INDEX
    Explanations

    clone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แบร
    -0.07
    maids
    -0.07
    WARE
    -0.07
    뱅
    -0.07
    uffers
    -0.06
    פאר
    -0.06
    幂
    -0.06
     explanatory
    -0.06
    배
    -0.06
     Â
    -0.06
    POSITIVE LOGITS
    图纸
    0.07
    رياضة
    0.07
     Tip
    0.07
     Gotham
    0.07
    uce
    0.07
     beta
    0.06
    日军
    0.06
     rapidement
    0.06
    起身
    0.06
    ół
    0.06
    Act Density 0.001%

    No Known Activations