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

    Neuronpedia

    INDEX
    Explanations

    say "up"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yep
    -0.07
     textbooks
    -0.06
    uitka
    -0.06
    .Plugin
    -0.06
     حافظ
    -0.06
    ควบค
    -0.06
    _lens
    -0.06
     Vec
    -0.06
    error
    -0.06
    ัปดาห
    -0.06
    POSITIVE LOGITS
    -definition
    0.06
    FFFF
    0.06
     goede
    0.06
     ört
    0.06
    .parents
    0.06
     joining
    0.06
     rebuilding
    0.06
    clidean
    0.06
    >/
    0.06
     electrode
    0.06
    Act Density 0.165%

    No Known Activations