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

    Neuronpedia

    INDEX
    Explanations

    documentation for return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oflav
    0.34
     whist
    0.34
     peritoneum
    0.33
     स्म
    0.33
    Wra
    0.33
    ﹟
    0.32
     rinsing
    0.32
    OGEN
    0.32
    Fock
    0.32
     wets
    0.31
    POSITIVE LOGITS
    ↵
    0.41
    iapan
    0.33
     современных
    0.33
    டாக
    0.33
     OWL
    0.32
     Fertility
    0.32
    どれ
    0.32
     Royalty
    0.32
    \)
    0.32
    equal
    0.31
    Act Density 0.011%

    No Known Activations