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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ha
    -0.07
    .code
    -0.07
     Vog
    -0.07
     Mathf
    -0.06
    .uid
    -0.06
     Mit
    -0.06
     במקרים
    -0.06
    霄
    -0.06
     הדברים
    -0.06
     Cyber
    -0.06
    POSITIVE LOGITS
    DCALL
    0.07
    饩
    0.07
     Hog
    0.07
    `.↵
    0.07
    鎮
    0.06
    _fn
    0.06
     been
    0.06
    [](
    0.06
    Activate
    0.06
    ﾒ
    0.06
    Act Density 0.004%

    No Known Activations