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

    Neuronpedia

    INDEX
    Explanations

    Arabic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     العالم
    -0.07
    _tracks
    -0.07
    符
    -0.07
    Ông
    -0.06
     студ
    -0.06
     parler
    -0.06
    揮
    -0.06
    짜
    -0.06
     пенс
    -0.06
    міну
    -0.06
    POSITIVE LOGITS
    sian
    0.07
    >>>>>>>>
    0.07
    Internal
    0.07
    fw
    0.06
     whatsoever
    0.06
    pery
    0.06
     strpos
    0.06
     checking
    0.06
    Java
    0.06
    ItemImage
    0.06
    Act Density 0.049%

    No Known Activations