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

    Neuronpedia

    INDEX
    Explanations

    Flask and ArgumentParser initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或其他
    0.43
    etapkan
    0.40
     Tully
    0.38
    🕺
    0.38
     TA
    0.37
    ahy
    0.37
     مذکور
    0.37
    ொரு
    0.36
    iyi
    0.36
    botao
    0.36
    POSITIVE LOGITS
    для
    0.44
    ीट
    0.42
    ;
    0.42
     karış
    0.41
     pequenas
    0.38
    טר
    0.37
    ();
    0.37
    。
    0.37
    )
    0.36
     uman
    0.34
    Act Density 0.033%

    No Known Activations