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

    Neuronpedia

    INDEX
    Explanations

    latex commands and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Raquete
    0.37
    接待
    0.36
    0.36
    endDate
    0.36
     فشاں
    0.36
    .-(
    0.36
     endDate
    0.36
    (“
    0.35
    🥐
    0.35
    🌽
    0.35
    POSITIVE LOGITS
    {\
    0.60
     {\
    0.56
    _{\
    0.52
     \
    0.51
    \
    0.46
    ]{\
    0.45
     "\
    0.44
    ensuremath
    0.44
    symbol
    0.43
    \,\
    0.43
    Act Density 0.001%

    No Known Activations