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

    Neuronpedia

    INDEX
    Explanations

    names and their beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.34
    G
    0.29
    E
    0.29
    O
    0.27
    M
    0.26
    D
    0.25
    кологи
    0.25
    i
    0.25
    ed
    0.25
    l
    0.24
    POSITIVE LOGITS
     puestos
    0.30
     zahlreiche
    0.30
     Allerdings
    0.30
     Photographs
    0.29
     einzige
    0.28
     allerdings
    0.28
     zahlreichen
    0.28
     sogenannte
    0.27
    ाने
    0.27
     mentre
    0.26
    Act Density 0.002%

    No Known Activations