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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    勇于
    -0.07
    �示
    -0.07
    ="../../../
    -0.07
     assignments
    -0.07
    对其进行
    -0.06
     submodule
    -0.06
     scav
    -0.06
    被称为
    -0.06
     Image
    -0.06
     thank
    -0.06
    POSITIVE LOGITS
    LESS
    0.07
    _statuses
    0.07
    	tr
    0.07
    CLK
    0.06
    CHA
    0.06
    º
    0.06
    Cr
    0.06
    /desktop
    0.06
     dp
    0.06
    ﺓ
    0.06
    Act Density 0.083%

    No Known Activations