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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conrad
    -0.07
    ек
    -0.07
     Accum
    -0.06
     deniz
    -0.06
     Starr
    -0.06
    -facing
    -0.06
     Ple
    -0.06
    병
    -0.06
    arts
    -0.06
     přiz
    -0.06
    POSITIVE LOGITS
    athon
    0.08
     vydání
    0.08
     vak
    0.07
    ?>"><?
    0.07
    ayah
    0.06
    essaging
    0.06
     jednání
    0.06
    .assignment
    0.06
    ,,
    0.06
    umm
    0.06
    Act Density 0.001%

    No Known Activations