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

    Neuronpedia

    INDEX
    Explanations

    spoken word attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Seite
    -1.12
    Коммента
    -1.07
    layın
    -1.04
     alábbi
    -1.04
    Материал
    -1.04
     verwijzen
    -1.02
     ladr
    -1.02
     улыба
    -0.99
    Portale
    -0.97
    Комментарий
    -0.97
    POSITIVE LOGITS
    [
    1.05
    ERO
    1.05
    を
    1.02
    ing
    1.01
    /"
    1.00
    ,.
    0.97
    ob
    0.96
    te
    0.96
    ter
    0.94
    は
    0.94
    Act Density 0.005%

    No Known Activations