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

    Neuronpedia

    INDEX
    Explanations

    voice commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agrant
    -0.08
    ㍍
    -0.08
    但这
    -0.07
    ################################
    -0.07
    ヅ
    -0.07
    Mil
    -0.07
    ㎿
    -0.07
     Clin
    -0.07
     fortunately
    -0.07
     Tomato
    -0.07
    POSITIVE LOGITS
     éléments
    0.07
    .Cells
    0.07
    	Read
    0.07
    ID
    0.07
    hh
    0.07
     Phar
    0.07
    罵
    0.07
     privileges
    0.07
    	position
    0.07
    _dn
    0.06
    Act Density 0.206%

    No Known Activations