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

    Neuronpedia

    INDEX
    Explanations

    million

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     урок
    -0.07
    oty
    -0.06
     знов
    -0.06
    _RADIO
    -0.06
    _INPUT
    -0.06
     robust
    -0.06
     MUST
    -0.06
    姉
    -0.06
    GRP
    -0.06
    られる
    -0.06
    POSITIVE LOGITS
    듯
    0.06
    alama
    0.06
    Uint
    0.06
     Interr
    0.06
    '',
    0.06
    makta
    0.06
    進行
    0.06
    ————————
    0.06
     Ban
    0.06
     :,
    0.06
    Act Density 0.017%

    No Known Activations