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

    Neuronpedia

    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thịt
    0.52
     Role
    0.52
     tigre
    0.48
     рост
    0.45
    <unused286>
    0.45
     Springfield
    0.45
     повышение
    0.45
     Deloitte
    0.44
     Woodstock
    0.44
     crece
    0.44
    POSITIVE LOGITS
    רה
    0.47
    uasion
    0.45
    𝗴
    0.45
    روع
    0.44
    ೇ
    0.44
    alien
    0.42
    𝔱
    0.42
    ᠯ
    0.42
    υ
    0.42
    ammatory
    0.41
    Act Density 0.001%

    No Known Activations