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

    Neuronpedia

    INDEX
    Explanations

    elongated sounds or words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polytopes
    0.39
     Polymers
    0.38
     Aeg
    0.37
     ανέ
    0.36
     conjure
    0.34
     evoke
    0.34
     বলিয়াছেন
    0.34
     marcher
    0.34
     curtail
    0.34
     marches
    0.34
    POSITIVE LOGITS
    aaaa
    1.29
    aaa
    1.29
    AAA
    1.27
    eeee
    1.26
     AAA
    1.23
    hhhh
    1.23
    EEEE
    1.23
    hhh
    1.22
    AAAA
    1.21
    pppp
    1.21
    Act Density 0.041%

    No Known Activations