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

    Neuronpedia

    INDEX
    Explanations

    drawbacks or comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拈
    0.41
    Ờ
    0.39
     atas
    0.38
     ORD
    0.38
    ILIO
    0.38
    बीयत
    0.37
    myX
    0.37
    Integral
    0.37
    ږ
    0.37
     médioc
    0.37
    POSITIVE LOGITS
     P
    0.44
     Scrib
    0.38
     Revol
    0.37
     stroj
    0.37
     downsides
    0.36
     Salam
    0.36
     Umwelt
    0.36
     downside
    0.36
     drawback
    0.36
    अर
    0.35
    Act Density 0.000%

    No Known Activations