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

    Neuronpedia

    INDEX
    Explanations

    versions of products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lieux
    0.45
    襷
    0.45
     endroits
    0.44
    まとめ
    0.44
     Schumer
    0.44
    श्किल
    0.42
     filmpje
    0.42
    нцикло
    0.41
     estratégico
    0.41
    決して
    0.41
    POSITIVE LOGITS
     of
    0.62
     produced
    0.59
     version
    0.57
     from
    0.54
     representing
    0.54
     版本
    0.52
     Version
    0.51
     versions
    0.48
    版
    0.48
     hergestellt
    0.48
    Act Density 0.065%

    No Known Activations