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

    Neuronpedia

    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitchell
    -0.07
    (buff
    -0.07
    ActionCreators
    -0.06
     مختلف
    -0.06
    大家
    -0.06
    _filenames
    -0.06
    Chuck
    -0.06
     neuronal
    -0.06
    _FRAGMENT
    -0.06
    Assembler
    -0.06
    POSITIVE LOGITS
    ذا
    0.07
     Follow
    0.07
     Baba
    0.06
    aliases
    0.06
    lac
    0.06
    argar
    0.06
    ُه
    0.06
    ¨ط
    0.06
     '::
    0.06
     rok
    0.06
    Act Density 0.014%

    No Known Activations