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

    Neuronpedia

    INDEX
    Explanations

    code, multiprocessing, mortal, breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     न्यायिक
    0.40
    washed
    0.40
     chlorine
    0.40
    భా
    0.39
    whitespace
    0.38
     चहल
    0.38
     kudu
    0.38
    🙈
    0.38
    भाई
    0.38
     repre
    0.37
    POSITIVE LOGITS
     cz
    0.40
    ப்படுத்து
    0.38
    無
    0.38
    无
    0.37
     Innov
    0.37
     all
    0.36
     Schwar
    0.35
     pieza
    0.35
     in
    0.34
    ப்பா
    0.34
    Act Density 0.000%

    No Known Activations