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

    Neuronpedia

    INDEX
    Explanations

    listing attributes or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pressur
    0.46
     wk
    0.43
    akeda
    0.43
     معم
    0.42
     Walter
    0.42
     عین
    0.42
     policym
    0.42
     foray
    0.42
     cilantro
    0.42
     programmatic
    0.41
    POSITIVE LOGITS
     и
    0.54
     மற்றும்
    0.54
    以及
    0.52
    埧
    0.52
    và
    0.50
    дження
    0.49
     및
    0.49
    льше
    0.49
    侸
    0.49
     మరియు
    0.48
    Act Density 0.002%

    No Known Activations