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
     bend
    -0.07
    ght
    -0.07
     Emit
    -0.06
    rase
    -0.06
    Ven
    -0.06
    cede
    -0.06
     тоді
    -0.06
    birthdate
    -0.06
     Txt
    -0.06
     sitting
    -0.06
    POSITIVE LOGITS
     CEOs
    0.06
     deadliest
    0.06
    การศ
    0.06
     DEST
    0.06
     druhý
    0.06
    .ID
    0.06
    <typeof
    0.06
    ')[
    0.06
     varios
    0.05
     hiking
    0.05
    Act Density 0.014%

    No Known Activations