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

    Neuronpedia

    INDEX
    Explanations

    Speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疯
    -0.07
     nécessaire
    -0.07
     ne
    -0.07
    cases
    -0.07
     ({
    -0.07
     Pb
    -0.07
     Cobb
    -0.07
    _prec
    -0.06
     لن
    -0.06
    🍃
    -0.06
    POSITIVE LOGITS
    encil
    0.08
    组合
    0.08
     mover
    0.08
    |`↵
    0.07
    تعل
    0.07
    Vac
    0.07
     userAgent
    0.07
     informs
    0.07
     bidding
    0.07
    DIM
    0.07
    Act Density 0.085%

    No Known Activations