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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babys
    -0.06
    こんに
    -0.06
     chết
    -0.06
     epis
    -0.06
    局
    -0.06
     bully
    -0.06
    沟
    -0.06
     setter
    -0.06
     IDS
    -0.06
     graduate
    -0.06
    POSITIVE LOGITS
     int
    0.06
     сила
    0.06
    uss
    0.06
    .tencent
    0.06
     "==
    0.06
     Wrapper
    0.06
    .super
    0.06
    �
    0.06
    ̀
    0.06
     李
    0.06
    Act Density 0.026%

    No Known Activations