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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Q
    -0.07
     Anne
    -0.07
     xlabel
    -0.07
    مست
    -0.07
     khỏe
    -0.07
    胸部
    -0.07
    净
    -0.07
    _Message
    -0.07
     OPT
    -0.07
    pring
    -0.07
    POSITIVE LOGITS
    	Field
    0.08
    �
    0.07
    ;a
    0.07
    这
    0.07
    停车场
    0.07
     Creation
    0.07
    ו
    0.06
     conj
    0.06
     files
    0.06
     Wouldn
    0.06
    Act Density 0.002%

    No Known Activations