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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    严å¯Ĩ
    -0.28
     directing
    -0.25
    croft
    -0.24
    за
    -0.24
     disb
    -0.24
    akra
    -0.24
    abouts
    -0.24
    ursal
    -0.23
     directed
    -0.23
     airs
    -0.23
    POSITIVE LOGITS
    ĥģ
    0.27
     ([[
    0.25
     comed
    0.24
    èĴľ
    0.24
    lij
    0.23
    UGHT
    0.23
    isti
    0.23
    лаг
    0.23
    setChecked
    0.23
    ä¸İåħ¶
    0.23
    Act Density 0.006%

    No Known Activations