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

    Neuronpedia

    INDEX
    Explanations

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     номер
    -0.07
    цип
    -0.07
    .FontStyle
    -0.07
    iegel
    -0.07
     והמ
    -0.07
    紧接着
    -0.07
     foregoing
    -0.07
    .ol
    -0.06
    ynom
    -0.06
    扊
    -0.06
    POSITIVE LOGITS
     plainly
    0.07
     Spawn
    0.07
    尽情
    0.07
    -frame
    0.07
    _sidebar
    0.06
    如何看待
    0.06
     хорошо
    0.06
    如期
    0.06
     współprac
    0.06
    ActionButton
    0.06
    Act Density 0.088%

    No Known Activations