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
    invoke
    -0.07
     architects
    -0.07
     priorities
    -0.06
    ่าย
    -0.06
     公
    -0.06
     Language
    -0.06
    earned
    -0.06
    getView
    -0.06
     proving
    -0.06
     trừ
    -0.06
    POSITIVE LOGITS
    Features
    0.06
     resigned
    0.06
     Crush
    0.06
     newText
    0.06
    Configs
    0.06
     Dropout
    0.06
     applicationContext
    0.06
    .GetText
    0.06
     سنگ
    0.06
    .getCode
    0.06
    Act Density 0.045%

    No Known Activations