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
    icular
    -0.07
    所谓
    -0.07
     Hygiene
    -0.07
     atmos
    -0.07
     baths
    -0.07
    -context
    -0.06
    cter
    -0.06
     Cosmetics
    -0.06
    geist
    -0.06
     Afro
    -0.06
    POSITIVE LOGITS
    plaatst
    0.08
     loft
    0.08
    (${
    0.08
     тракт
    0.08
    ಅ
    0.08
    ඩ
    0.07
    /${
    0.07
     (${
    0.07
    ತಿಯಿಂದ
    0.07
    ej
    0.07
    Act Density 0.005%

    No Known Activations