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

    Neuronpedia

    INDEX
    Explanations

    describing attributes and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.49
    ästä
    0.47
    ia
    0.47
    ts
    0.47
    ies
    0.46
     I
    0.45
    ation
    0.45
    ses
    0.45
    .\
    0.44
    sl
    0.44
    POSITIVE LOGITS
     puns
    0.45
     polinom
    0.43
    았던
    0.43
     наличие
    0.41
     qualités
    0.41
     dúvidas
    0.41
     dudas
    0.41
     publicaciones
    0.40
     pembahasan
    0.40
     hạnh
    0.39
    Act Density 0.124%

    No Known Activations