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

    Neuronpedia

    INDEX
    Explanations

    conditional expression (if/else)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.59
    ل
    0.51
    ری
    0.48
    نا
    0.46
    ர்
    0.46
    ർ
    0.43
    मा
    0.42
    ند
    0.42
    мо
    0.42
    N
    0.41
    POSITIVE LOGITS
     in
    0.48
     Pokud
    0.44
     في
    0.42
    </h3>
    0.41
    </h2>
    0.38
     impenetrable
    0.37
     patios
    0.36
     obscures
    0.35
    0.35
     Nếu
    0.35
    Act Density 3.017%

    No Known Activations