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

    Neuronpedia

    INDEX
    Explanations

    autocomplete disabled globally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ре
    0.48
     철
    0.48
    ）
    0.46
    시
    0.46
    ри
    0.45
    λί
    0.45
    工作
    0.45
    ку
    0.42
    取消
    0.42
    베
    0.41
    POSITIVE LOGITS
    畊
    0.47
     consac
    0.44
     "":
    0.43
     $:=$
    0.43
    茧
    0.43
     intitul
    0.41
     bazie
    0.41
     institut
    0.40
    ziehungs
    0.40
     spont
    0.40
    Act Density 0.000%

    No Known Activations