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

    Neuronpedia

    INDEX
    Explanations

    -term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ima
    -0.06
    _CL
    -0.06
    ανου
    -0.06
    outes
    -0.06
     Apocalypse
    -0.06
    _QU
    -0.06
    Allen
    -0.06
     halls
    -0.06
    )";↵
    -0.06
     ),↵↵
    -0.06
    POSITIVE LOGITS
     одному
    0.07
    ologi
    0.07
    _supported
    0.07
     metropolitan
    0.07
     confess
    0.06
    mour
    0.06
    lica
    0.06
    ugar
    0.06
    πι
    0.06
     �
    0.06
    Act Density 0.012%

    No Known Activations