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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    klä
    -0.07
    lique
    -0.07
    792
    -0.07
    letes
    -0.06
     phù
    -0.06
    lug
    -0.06
    ponses
    -0.06
    ruba
    -0.06
     IDb
    -0.06
    pline
    -0.06
    POSITIVE LOGITS
    cılar
    0.07
     "/
    0.06
     standart
    0.06
     prioritize
    0.06
    .Info
    0.06
    óg
    0.06
    (ls
    0.06
     Επ
    0.06
    FileChooser
    0.06
     Ere
    0.06
    Act Density 0.067%

    No Known Activations