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

    Neuronpedia

    INDEX
    Explanations

    `8">` prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tiket
    1.49
    tok
    1.49
    𝚆
    1.40
    seva
    1.39
    t
    1.38
     निकालने
    1.36
    гите
    1.33
    тено
    1.32
     psychosis
    1.29
     inroads
    1.28
    POSITIVE LOGITS
    ע
    1.53
    ज
    1.49
     gripe
    1.47
     составля
    1.37
     PPS
    1.35
    honey
    1.34
     всей
    1.32
    ValueLayout
    1.30
     изобра
    1.27
     kanggo
    1.26
    Act Density 0.002%

    No Known Activations