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

    Neuronpedia

    INDEX
    Explanations

    SECOND

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predict
    -0.07
     ner
    -0.07
     dormant
    -0.07
     significant
    -0.06
     contribute
    -0.06
    _nc
    -0.06
     Vo
    -0.06
    差
    -0.06
     ppm
    -0.06
    pricing
    -0.06
    POSITIVE LOGITS
    _toggle
    0.07
    自行车
    0.07
    밨
    0.07
     Able
    0.07
    ᎑
    0.07
     Sociology
    0.07
     mailbox
    0.07
    过去
    0.07
    ᵭ
    0.06
    ꧊
    0.06
    Act Density 0.001%

    No Known Activations