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

    Neuronpedia

    INDEX
    Explanations

    Travel tickets and passes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timing
    -0.06
    ?[
    -0.06
     nome
    -0.06
     Gaussian
    -0.06
    iate
    -0.06
     Debugger
    -0.06
     sắc
    -0.06
    todo
    -0.06
    Helpers
    -0.06
     illumination
    -0.06
    POSITIVE LOGITS
     shiny
    0.07
    .ForegroundColor
    0.07
     JO
    0.07
    _CONT
    0.06
     아�
    0.06
    ');
↵
    0.06
     chic
    0.06
    Ř
    0.06
     поступ
    0.06
     translate
    0.06
    Act Density 0.017%

    No Known Activations