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

    Neuronpedia

    INDEX
    Explanations

    household bleach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ви
    1.10
    ̪
    1.06
    okhlov
    1.05
    1.02
     симпто
    1.01
     GDPPC
    1.00
     Attractions
    1.00
    tekn
    0.98
    उन्होंने
    0.96
    肐
    0.96
    POSITIVE LOGITS
    스와
    1.01
    drops
    0.88
    id
    0.85
    ist
    0.84
    າວ
    0.80
     seam
    0.77
     relat
    0.75
     wis
    0.74
     subst
    0.74
    ছা
    0.74
    Act Density 0.000%

    No Known Activations