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

    Neuronpedia

    INDEX
    Explanations

    sentence starters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ന്ത്രാ
    0.32
     разнови
    0.31
     simonsen
    0.31
    PAssignment
    0.31
     "¿
    0.31
     Eurostile
    0.30
     pequeñas
    0.30
     корпора
    0.30
     globales
    0.30
     ziff
    0.30
    POSITIVE LOGITS
    It
    0.30
    On
    0.28
    2
    0.28
    C
    0.27
    At
    0.26
    1
    0.26
    7
    0.26
    He
    0.26
    5
    0.26
    A
    0.25
    Act Density 4.846%

    No Known Activations