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

    Neuronpedia

    INDEX
    Explanations

    printed circuit boards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    藏着
    -0.08
    か
    -0.07
    也随之
    -0.07
    堪
    -0.07
    出处
    -0.07
     cautiously
    -0.07
    ˚
    -0.06
    assis
    -0.06
    赘
    -0.06
    ("%
    -0.06
    POSITIVE LOGITS
     Rangers
    0.08
     Wroc
    0.08
     trolling
    0.08
    GPU
    0.07
    שטח
    0.07
    .getStyle
    0.07
    	View
    0.07
     wsp
    0.07
    プラ
    0.07
    _DISABLE
    0.07
    Act Density 0.022%

    No Known Activations