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

    Neuronpedia

    INDEX
    Explanations

    in our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     douze
    0.47
     ennemis
    0.46
    テー
    0.46
     감소
    0.45
     semblables
    0.44
     publique
    0.43
    コンピュー
    0.43
     デザイン
    0.43
     cancelButton
    0.43
     кеңселер
    0.43
    POSITIVE LOGITS
    etan
    0.47
    form
    0.46
    pt
    0.44
    e
    0.44
     Ex
    0.43
     Inspect
    0.43
     bpy
    0.41
    Jurassic
    0.41
     Kur
    0.41
    Kur
    0.41
    Act Density 0.000%

    No Known Activations