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

    Neuronpedia

    INDEX
    Explanations

    varies based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bekommen
    0.42
     brasil
    0.42
     anderen
    0.41
     vivo
    0.39
     ecol
    0.39
     estud
    0.38
     cortex
    0.38
     aguas
    0.38
     preferences
    0.38
     disseminate
    0.38
    POSITIVE LOGITS
     νέ
    0.47
     ㅛ
    0.47
    ként
    0.45
    alık
    0.45
    ếp
    0.43
     독
    0.42
    𝘾
    0.41
     Από
    0.41
    ifié
    0.40
    vě
    0.40
    Act Density 0.006%

    No Known Activations