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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alonso
    -0.07
    ﻠ
    -0.06
    ยอด
    -0.06
     Producer
    -0.06
    /loader
    -0.06
    uce
    -0.06
    -commerce
    -0.06
     нескольких
    -0.06
     радян
    -0.06
    iendo
    -0.06
    POSITIVE LOGITS
    ￣
    0.07
    :model
    0.07
    he
    0.07
     requ
    0.06
    engl
    0.06
    สว
    0.06
    (last
    0.06
    choices
    0.06
    ...)
    0.06
    rios
    0.06
    Act Density 0.034%

    No Known Activations