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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    middlewares
    -0.07
    ประจำ
    -0.06
     strcat
    -0.06
    ibraries
    -0.06
     Manhattan
    -0.06
     захоп
    -0.06
    .split
    -0.06
    ाहक
    -0.06
     tucked
    -0.06
    pletely
    -0.06
    POSITIVE LOGITS
     aroma
    0.07
    ssc
    0.07
     SQ
    0.06
    mg
    0.06
     announces
    0.06
    	desc
    0.06
    malı
    0.06
     DOT
    0.06
     sag
    0.06
    関
    0.06
    Act Density 0.012%

    No Known Activations