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

    Neuronpedia

    INDEX
    Explanations

    Censys, Pwnagotchi, opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jars
    0.39
     encycl
    0.39
    ency
    0.38
     Flush
    0.38
    نز
    0.36
    נטי
    0.36
    젝
    0.36
    歙
    0.36
     ponctuées
    0.36
    介绍
    0.35
    POSITIVE LOGITS
     conveys
    0.42
     اخذت
    0.41
     kiwi
    0.41
     jobs
    0.40
     ungefähr
    0.39
     took
    0.39
    Voice
    0.39
     কণ্
    0.38
     signify
    0.38
     Voice
    0.38
    Act Density 0.004%

    No Known Activations