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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     techno
    -0.07
     jeszcze
    -0.07
     qr
    -0.07
    Curso
    -0.07
    nými
    -0.07
    	source
    -0.07
     plea
    -0.06
     viele
    -0.06
    undefined
    -0.06
    /welcome
    -0.06
    POSITIVE LOGITS
    incess
    0.06
    嘉
    0.06
    ju
    0.06
    .scrollTop
    0.06
    useum
    0.06
    만남
    0.06
    fung
    0.06
     meticulously
    0.06
     agrees
    0.06
    _Server
    0.06
    Act Density 0.009%

    No Known Activations