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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testers
    -0.07
     disparities
    -0.07
     Logan
    -0.06
    λής
    -0.06
    lm
    -0.06
    isini
    -0.06
     торгов
    -0.06
    /Base
    -0.06
    -types
    -0.06
    _rule
    -0.06
    POSITIVE LOGITS
     Loy
    0.07
     ГО
    0.06
    यर
    0.06
    _NAME
    0.06
     identifies
    0.06
     Blue
    0.06
    Viol
    0.06
    子的
    0.06
     pretrained
    0.06
     STRUCT
    0.06
    Act Density 0.012%

    No Known Activations