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

    Neuronpedia

    INDEX
    Explanations

    be specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅಥವಾ
    0.40
     respal
    0.38
     perfecta
    0.37
    requencies
    0.37
     或
    0.36
    或
    0.36
     flow
    0.36
    न्दी
    0.36
     statutes
    0.35
    rystals
    0.35
    POSITIVE LOGITS
    hluk
    0.42
    gete
    0.39
    gele
    0.38
    ulia
    0.37
    ▷
    0.37
    ढ़ा
    0.36
     අන
    0.36
    两国
    0.36
    are
    0.35
    ärk
    0.35
    Act Density 0.012%

    No Known Activations