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

    Neuronpedia

    INDEX
    Explanations

    either or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஆடி
    0.46
     થઇ
    0.46
    まだ
    0.45
    зирован
    0.44
    Respond
    0.43
    RenderTarget
    0.43
    ający
    0.41
    udu
    0.41
    ар
    0.40
    ak
    0.40
    POSITIVE LOGITS
     tum
    0.46
     eels
    0.45
     parentheses
    0.44
     حف
    0.44
     paréntesis
    0.43
     Scandinavian
    0.43
     enchant
    0.43
     abc
    0.42
     অল্প
    0.42
     វា
    0.42
    Act Density 0.004%

    No Known Activations