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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fav
    -0.06
    от
    -0.06
    -final
    -0.06
    _XDECREF
    -0.06
    (sign
    -0.06
    .square
    -0.06
    _literals
    -0.06
     phát
    -0.06
    (ent
    -0.06
     Townsend
    -0.06
    POSITIVE LOGITS
     듯
    0.08
     /*!
    0.07
    ‘s
    0.07
     ๆ
    0.07
     ещё
    0.06
     Roads
    0.06
    mış
    0.06
    );
↵
    0.06
    ственная
    0.06
    OptionsMenu
    0.06
    Act Density 0.028%

    No Known Activations