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

    Neuronpedia

    INDEX
    Explanations

    PTH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ограф
    -0.07
    早点
    -0.07
    (bot
    -0.07
    尚未
    -0.07
    �
    -0.07
    Ý
    -0.07
     amet
    -0.06
    سحب
    -0.06
    ATH
    -0.06
    пит
    -0.06
    POSITIVE LOGITS
     "";
    0.08
     *);↵
    0.07
     Four
    0.07
     rağmen
    0.07
    ']↵↵↵
    0.07
     menstrual
    0.07
    AndFeel
    0.07
     [];
    0.07
     לפעמים
    0.07
    '])
↵
    0.07
    Act Density 0.001%

    No Known Activations