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

    Neuronpedia

    INDEX
    Explanations

    Option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нів
    0.52
    cakes
    0.52
     ট্র
    0.50
    篆
    0.48
     auxqu
    0.48
    combined
    0.47
    Ŷ
    0.47
    γκε
    0.47
    ահ
    0.46
     suffisante
    0.46
    POSITIVE LOGITS
     período
    0.47
     any
    0.46
    wärt
    0.46
    ق
    0.46
     prism
    0.44
    ഈ
    0.44
     argues
    0.43
     destroys
    0.43
     near
    0.43
     interpre
    0.42
    Act Density 0.111%

    No Known Activations