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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isArray
    -0.07
     ।↵
    -0.06
     rectangles
    -0.06
    残
    -0.06
    _slider
    -0.06
    аша
    -0.06
    bon
    -0.06
     누
    -0.06
     protagonists
    -0.06
    antiago
    -0.06
    POSITIVE LOGITS
    _DISPLAY
    0.09
    -make
    0.07
    ृ
    0.06
     دولت
    0.06
     Clean
    0.06
     government
    0.06
    田
    0.06
    mk
    0.06
    Transport
    0.06
    —not
    0.06
    Act Density 0.006%

    No Known Activations