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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    assumption
    0.43
    峋
    0.42
    <unused207>
    0.41
     rumus
    0.40
    aphthal
    0.40
    ","-
    0.40
     रमेश
    0.39
     nisid
    0.39
    akkhan
    0.38
     顔
    0.38
    POSITIVE LOGITS
    s
    0.47
    ご
    0.46
    ی
    0.46
    ک
    0.45
    AS
    0.44
     lessons
    0.43
    BRO
    0.43
    GTA
    0.43
    ا
    0.42
    WA
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.