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

    Neuronpedia

    INDEX
    Explanations

    help me refine or tailor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ための
    1.21
    स
    1.09
    iv
    1.08
    soever
    1.05
    I
    1.03
    ной
    0.96
    されます
    0.93
    かが
    0.93
     fizer
    0.93
     danno
    0.93
    POSITIVE LOGITS
     podríamos
    1.27
    क्षिप्त
    1.18
    ień
    1.14
    ấm
    1.10
     まま
    1.10
     aastal
    1.09
     člove
    1.08
     sejarah
    1.07
     położ
    1.07
     Při
    1.07
    Act Density 0.078%

    No Known Activations