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

    Neuronpedia

    INDEX
    Explanations

    what if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ைத்
    0.45
    ந்த
    0.45
     substituted
    0.44
    ச்சல்
    0.44
     highs
    0.43
     integrative
    0.43
    гети
    0.42
    затор
    0.41
    نمية
    0.41
     policymakers
    0.41
    POSITIVE LOGITS
     i
    0.54
    awat
    0.52
    ()/
    0.52
    Bars
    0.50
    King
    0.50
    Guides
    0.49
    aturan
    0.48
     وتح
    0.48
    Bois
    0.48
    Philosophy
    0.48
    Act Density 0.000%

    No Known Activations