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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    簪
    -0.08
    참
    -0.08
    子孙
    -0.07
    /un
    -0.07
     guise
    -0.06
    أماكن
    -0.06
    Addon
    -0.06
    /tags
    -0.06
    筵
    -0.06
    canf
    -0.06
    POSITIVE LOGITS
    봇
    0.07
     shrinking
    0.07
     radioButton
    0.07
     Architect
    0.07
     quelle
    0.07
     Vì
    0.07
    죄
    0.07
    .writer
    0.06
    华尔街
    0.06
    adro
    0.06
    Act Density 0.010%

    No Known Activations