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

    Neuronpedia

    INDEX
    Explanations

    Code/database snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vex
    -0.07
     pequ
    -0.07
     Dive
    -0.07
    emption
    -0.07
     SUV
    -0.07
    <pcl
    -0.06
     evacuate
    -0.06
     burg
    -0.06
    攸
    -0.06
     punch
    -0.06
    POSITIVE LOGITS
    Solid
    0.07
    (Android
    0.07
     дела
    0.07
    ận
    0.07
    𫭟
    0.07
     clase
    0.07
    物件
    0.07
    French
    0.07
    REFERENCES
    0.07
    业内人士
    0.07
    Act Density 0.001%

    No Known Activations