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

    Neuronpedia

    INDEX
    Explanations

    transparent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auto
    -0.07
    most
    -0.07
     لأ
    -0.07
     Copy
    -0.07
    /post
    -0.07
    GET
    -0.06
    博弈
    -0.06
     Cly
    -0.06
    +"</
    -0.06
    	put
    -0.06
    POSITIVE LOGITS
     anlaş
    0.08
    젔
    0.07
     созда
    0.07
    _restore
    0.07
    _REFRESH
    0.06
     dens
    0.06
     kans
    0.06
    (levels
    0.06
     enchanted
    0.06
    빅
    0.06
    Act Density 0.001%

    No Known Activations