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

    Neuronpedia

    INDEX
    Explanations

    synonym/similar meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他的
    0.35
    ↵↵
    0.32
     акций
    0.29
     ब्राउन
    0.29
    表演
    0.28
     cujo
    0.28
    न
    0.28
     गवर्नर
    0.27
     Fungsi
    0.27
     Novo
    0.27
    POSITIVE LOGITS
     be
    0.32
     as
    0.31
    ہ
    0.29
    pore
    0.28
    t
    0.26
    parks
    0.26
    то
    0.26
     mydb
    0.26
     bushels
    0.26
    cimiento
    0.25
    Act Density 0.019%

    No Known Activations