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

    Neuronpedia

    INDEX
    Explanations

    resource directories and help sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.97
     (=
    0.95
     (
    0.94
     that
    0.94
     (?)
    0.93
    0.92
    的
    0.92
    [(
    0.91
    $,
    0.90
    Ди
    0.89
    POSITIVE LOGITS
     viajeros
    1.01
     şirket
    0.97
    വന്‍
    0.95
     partners
    0.95
     licensees
    0.95
     allies
    0.94
     compañías
    0.93
     konkre
    0.92
     fabricants
    0.92
     país
    0.92
    Act Density 0.029%

    No Known Activations