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

    Neuronpedia

    INDEX
    Explanations

    words ending in z

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.44
    নকে
    0.44
    reten
    0.41
     стать
    0.40
    outube
    0.39
    கிறது
    0.39
    stituted
    0.39
    წერ
    0.39
     कथन
    0.39
    南方
    0.38
    POSITIVE LOGITS
    ়
    0.70
    ्ड
    0.60
    ير
    0.50
    ек
    0.47
    ァ
    0.47
    нодоро
    0.46
    ̇
    0.46
    ookeeper
    0.46
    ィ
    0.46
    krieg
    0.43
    Act Density 0.047%

    No Known Activations