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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grij
    0.42
    Automat
    0.42
    Activate
    0.41
    ING
    0.40
    AUT
    0.39
    (())
    0.39
     consentement
    0.38
    pady
    0.38
    ule
    0.38
    lle
    0.38
    POSITIVE LOGITS
    撓
    0.49
     peculiarly
    0.46
    нять
    0.46
     relieving
    0.45
     اقصیٰ
    0.45
     explorers
    0.44
     ʼ
    0.44
    ﮗ
    0.44
     Бы
    0.43
     Thieves
    0.43
    Act Density 0.000%

    No Known Activations