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

    Neuronpedia

    INDEX
    Explanations

    Quality varies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    گم
    0.43
    Leaving
    0.42
    फारिश
    0.39
     ship
    0.38
    ೆಂಟ್
    0.38
    情緒
    0.37
    mailing
    0.37
    屈
    0.37
     watercolors
    0.37
    🖒
    0.37
    POSITIVE LOGITS
     CHD
    0.50
    ovaný
    0.46
     TDI
    0.45
    ytics
    0.43
     CFA
    0.43
     theta
    0.42
     trusted
    0.42
     Mek
    0.41
     Layer
    0.41
    ల్‌
    0.40
    Act Density 0.000%

    No Known Activations