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

    Neuronpedia

    INDEX
    Explanations

    Mountain ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manuals
    -0.07
    ervlet
    -0.07
    bang
    -0.06
    administration
    -0.06
     arts
    -0.06
     Щ
    -0.06
    تباط
    -0.06
    asp
    -0.06
    flen
    -0.06
     clue
    -0.06
    POSITIVE LOGITS
    ivic
    0.07
    二
    0.06
    ALLERY
    0.06
     directory
    0.06
    unci
    0.06
    ivol
    0.06
    _directory
    0.06
     Jehovah
    0.06
     Rupert
    0.06
    ']."
    0.06
    Act Density 0.072%

    No Known Activations