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

    Neuronpedia

    INDEX
    Explanations

    making things happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Response
    0.33
    isering
    0.33
     تمامی
    0.32
    wegian
    0.32
    ской
    0.31
    5
    0.31
    یک
    0.30
    esta
    0.30
    ные
    0.30
    isi
    0.30
    POSITIVE LOGITS
     allows
    0.32
     gives
    0.31
     conducive
    0.30
     decentral
    0.28
     enables
    0.28
    ρίας
    0.27
     distância
    0.27
     pozwala
    0.27
    ล
    0.27
     безопасности
    0.27
    Act Density 0.367%

    No Known Activations