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

    Neuronpedia

    INDEX
    Explanations

    Netherlands historically, findings show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Las
    0.48
    Rh
    0.46
    Sy
    0.43
    Michael
    0.43
    Г
    0.43
    Ж
    0.43
     classes
    0.42
    Dans
    0.42
     तीस
    0.41
    Но
    0.41
    POSITIVE LOGITS
    nmid
    0.49
    ព័ន្ធ
    0.47
    cents
    0.45
    \<^
    0.45
    pricing
    0.44
     (\%)
    0.44
    䟧
    0.44
     എന്നാല്‍
    0.43
    stellungs
    0.43
    cular
    0.43
    Act Density 0.000%

    No Known Activations