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

    Neuronpedia

    INDEX
    Explanations

    able, possible, feasible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    1.49
    ing
    1.34
    но
    1.32
    𝐞
    1.30
    required
    1.26
    ри
    1.24
    まるで
    1.24
    てください
    1.21
    ever
    1.19
    ../../
    1.18
    POSITIVE LOGITS
     homicide
    1.23
     terrain
    1.10
    bara
    1.08
     спорттук
    1.06
     мелдеш
    1.05
    範囲
    1.04
    ItemBackground
    1.03
     latitudes
    1.01
     aisément
    0.99
     mismatch
    0.99
    Act Density 0.212%

    No Known Activations