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

    Neuronpedia

    INDEX
    Explanations

    approximations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    אָ
    0.43
    Ἔ
    0.43
    Extend
    0.41
     annotate
    0.40
    ಲೇ
    0.39
     velocità
    0.39
    INES
    0.39
     ткань
    0.39
    ≲
    0.38
    Herk
    0.38
    POSITIVE LOGITS
     relevant
    0.42
     nerdy
    0.41
     needed
    0.41
    嫡
    0.40
     Royce
    0.40
     notches
    0.39
    招聘
    0.39
    দর্শী
    0.39
     Shadow
    0.38
     свого
    0.38
    Act Density 0.003%

    No Known Activations