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
     sw
    -0.06
     sleeping
    -0.06
     riv
    -0.06
    _arrow
    -0.06
     patt
    -0.06
    'я
    -0.06
     […]
    -0.06
    razier
    -0.05
    verter
    -0.05
     buddies
    -0.05
    POSITIVE LOGITS
     crafting
    0.07
     xã
    0.07
    (RuntimeObject
    0.07
    _IL
    0.07
    OTTOM
    0.07
    ynomials
    0.06
    Further
    0.06
     докум
    0.06
     FileNotFoundError
    0.06
     RCS
    0.06
    Act Density 0.254%

    No Known Activations