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

    Neuronpedia

    INDEX
    Explanations

    geographic and performance boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ay
    0.42
    on
    0.42
    Además
    0.42
    im
    0.41
    ORITY
    0.41
    an
    0.41
    𝗻
    0.40
    или
    0.40
    iting
    0.39
    अधिकांश
    0.39
    POSITIVE LOGITS
     thrombo
    0.44
     hémorro
    0.43
     Koj
    0.42
     qua
    0.42
     sap
    0.40
    ….
    0.39
     thiol
    0.39
    ثر
    0.37
     covalently
    0.37
     cog
    0.37
    Act Density 0.022%

    No Known Activations