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

    Neuronpedia

    INDEX
    Explanations

    parts of objects and clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.28
    5
    0.26
     cinéma
    0.24
    4
    0.24
    7
    0.24
    _
    0.24
    Cinema
    0.23
    =
    0.23
    지
    0.22
     cylinder
    0.21
    POSITIVE LOGITS
     for
    0.34
    ra
    0.26
     DOJ
    0.23
     odgov
    0.23
     SULF
    0.22
    很多的
    0.22
    odik
    0.22
    rk
    0.22
     ApJ
    0.22
    for
    0.21
    Act Density 0.254%

    No Known Activations