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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wifi
    -0.07
    ஜ
    -0.07
    -sw
    -0.07
     twisting
    -0.07
    五月
    -0.07
    _Test
    -0.06
    -java
    -0.06
    Win
    -0.06
    小说
    -0.06
     warning
    -0.06
    POSITIVE LOGITS
    (EC
    0.07
    %'
    0.07
    ку
    0.07
     .'
    0.07
    .Tag
    0.07
     Ecuador
    0.07
    槊
    0.07
    ECT
    0.07
    éis
    0.07
    就在于
    0.06
    Act Density 0.006%

    No Known Activations