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

    Neuronpedia

    INDEX
    Explanations

    linking related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sembling
    1.43
    𝑵
    1.37
    ℏ
    1.30
    ging
    1.27
     Flare
    1.27
    😪
    1.26
    𝐼
    1.26
     Conditions
    1.26
    cluding
    1.22
     Definitions
    1.19
    POSITIVE LOGITS
    autonomous
    1.30
    ্তার
    1.26
    োম
    1.21
     forg
    1.20
     ঢুক
    1.18
     meravigli
    1.17
    ä
    1.16
    良好的
    1.15
    ه
    1.15
     지금까지
    1.15
    Act Density 0.000%

    No Known Activations