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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟋
    0.49
     FIGURES
    0.46
     vitre
    0.45
    ＂
    0.43
     obchod
    0.42
     univariate
    0.42
     Diarsipkan
    0.42
    这篇文章
    0.42
     chromatographic
    0.42
     Coleoptera
    0.41
    POSITIVE LOGITS
    ause
    0.53
    oke
    0.48
    ale
    0.46
    ree
    0.46
    air
    0.46
    low
    0.46
    hi
    0.45
    uh
    0.45
    elo
    0.44
    ira
    0.44
    Act Density 0.000%

    No Known Activations