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

    Neuronpedia

    INDEX
    Explanations

    adjust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cb
    -0.07
    azer
    -0.07
    ủng
    -0.07
    .workspace
    -0.06
    /storage
    -0.06
     lazım
    -0.06
    ela
    -0.06
    izer
    -0.06
    ayers
    -0.06
    際
    -0.06
    POSITIVE LOGITS
     дії
    0.07
    бин
    0.07
    溫
    0.06
    	unit
    0.06
    .↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     لل
    0.06
     clientele
    0.06
    mile
    0.06
     fiscal
    0.06
     품
    0.06
    Act Density 0.027%

    No Known Activations