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

    Neuronpedia

    INDEX
    Explanations

    list enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ebenso
    0.28
     erste
    0.26
     først
    0.26
     pertama
    0.26
    」「
    0.25
     প্রথমেই
    0.25
     primeiro
    0.25
    ，
    0.25
     veya
    0.25
     bildet
    0.24
    POSITIVE LOGITS
     ஆகிய
    0.32
     infine
    0.30
     എന്നിവ
    0.29
     ஆகியவை
    0.29
    Ultimately
    0.28
     ultimately
    0.27
     importantly
    0.26
     lastly
    0.26
     bref
    0.25
     whatnot
    0.25
    Act Density 1.752%

    No Known Activations