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

    Neuronpedia

    INDEX
    Explanations

    android imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jury
    0.45
    highest
    0.45
    orro
    0.44
    கடந்த
    0.43
    नई
    0.43
    goatee
    0.43
    interpret
    0.42
    ly
    0.42
    ॉम
    0.42
    ugo
    0.41
    POSITIVE LOGITS
     عنوان
    0.38
     Ded
    0.37
     Swift
    0.36
     Mumbai
    0.35
    setEmail
    0.35
     katika
    0.34
     Chicago
    0.34
     (
    0.33
     location
    0.33
     initially
    0.33
    Act Density 0.001%

    No Known Activations