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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ckpt
    -0.07
    龈
    -0.06
    _bn
    -0.06
    tón
    -0.06
    明代
    -0.06
    ---@
    -0.06
    赏析
    -0.06
    ZO
    -0.06
    یر
    -0.06
    지를
    -0.06
    POSITIVE LOGITS
     Cav
    0.08
    �
    0.07
    สา
    0.07
     방
    0.07
    Permission
    0.07
     Couch
    0.07
     getActivity
    0.07
     Pastor
    0.07
     fetus
    0.07
    UILDER
    0.07
    Act Density 0.015%

    No Known Activations