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

    Neuronpedia

    INDEX
    Explanations

    String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    險
    -0.06
     abound
    -0.06
    的手
    -0.06
     человеч
    -0.06
    莫
    -0.06
    /site
    -0.06
    랙
    -0.06
    」「
    -0.06
     opendir
    -0.06
     controversies
    -0.06
    POSITIVE LOGITS
    	If
    0.07
     hypotheses
    0.07
    (fi
    0.07
    Parent
    0.07
     melhor
    0.07
     costume
    0.06
     self
    0.06
    Amy
    0.06
    ú
    0.06
     phi
    0.06
    Act Density 0.000%

    No Known Activations