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

    Neuronpedia

    INDEX
    Explanations

    parenthetical remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    地方
    0.46
    ي
    0.45
    ኝ
    0.44
    രെ
    0.44
    স্বাস্থ্য
    0.44
     Presse
    0.44
     Consulta
    0.44
     Política
    0.43
    州
    0.43
    犯罪
    0.42
    POSITIVE LOGITS
     piss
    0.49
     ഈ
    0.46
    ppel
    0.46
    MGMT
    0.44
     appBar
    0.43
     ид
    0.43
     hinn
    0.42
     interv
    0.41
     kontroll
    0.41
     split
    0.41
    Act Density 0.000%

    No Known Activations