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

    Neuronpedia

    INDEX
    Explanations

    colors in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    硙
    0.42
    犍
    0.41
     জড়ের
    0.41
     albi
    0.41
    狒
    0.41
    嵇
    0.41
    🧺
    0.40
    ViewController
    0.39
     egal
    0.39
    Predicate
    0.39
    POSITIVE LOGITS
     blue
    1.30
     green
    1.21
    blue
    1.16
     orange
    1.11
     purple
    1.09
     red
    1.05
     Blue
    1.05
    green
    1.02
     blau
    0.98
    orange
    0.97
    Act Density 0.053%

    No Known Activations