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

    Neuronpedia

    INDEX
    Explanations

    musical chords (C, G, Am, F)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noises
    0.39
    ეგისტრ
    0.39
     dùng
    0.38
     ဆို
    0.38
     delet
    0.37
     смысла
    0.37
    ⱪ
    0.37
     gamer
    0.37
     usato
    0.37
     spacings
    0.36
    POSITIVE LOGITS
    embedding
    0.40
    ज
    0.38
    ijing
    0.37
    swift
    0.35
    dington
    0.35
    chée
    0.35
    castle
    0.34
    datasets
    0.34
    ess
    0.34
    ઝ
    0.34
    Act Density 0.005%

    No Known Activations