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

    Neuronpedia

    INDEX
    Explanations

    English sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]))↵↵
    -0.08
     다양한
    -0.07
     Eval
    -0.07
    middle
    -0.07
     Kal
    -0.07
     이상
    -0.06
     efect
    -0.06
     Picks
    -0.06
    	info
    -0.06
     кілька
    -0.06
    POSITIVE LOGITS
     Siemens
    0.06
    馆
    0.06
     ($(
    0.06
    ;'↵
    0.06
     bởi
    0.06
    -alert
    0.06
     "></
    0.06
     Záp
    0.06
     sitio
    0.06
    .Api
    0.06
    Act Density 0.228%

    No Known Activations