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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pl
    -0.07
     sustaining
    -0.07
    _Item
    -0.07
     neutrality
    -0.07
    节点
    -0.06
     complement
    -0.06
    osl
    -0.06
    ord
    -0.06
    όν
    -0.06
    ndern
    -0.06
    POSITIVE LOGITS
     jer
    0.07
     tvor
    0.06
    反
    0.06
    Mozilla
    0.06
    /Sub
    0.06
    Americ
    0.06
    +len
    0.06
     жов
    0.06
     терап
    0.06
     irregular
    0.05
    Act Density 0.014%

    No Known Activations