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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Completion
    -0.07
     verz
    -0.07
    🖌
    -0.07
    WithContext
    -0.07
     Phonetic
    -0.07
     Gmail
    -0.07
    .KeyChar
    -0.06
     generalize
    -0.06
     اعت
    -0.06
    DefaultCloseOperation
    -0.06
    POSITIVE LOGITS
     deficiency
    0.08
    очка
    0.07
     pd
    0.07
    出击
    0.07
    可能会
    0.07
    因素
    0.07
     indicators
    0.07
     notorious
    0.07
    альная
    0.07
     Views
    0.07
    Act Density 0.001%

    No Known Activations