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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tracked
    -0.07
    _submit
    -0.07
    켚
    -0.07
    巴萨
    -0.07
    Raw
    -0.07
     whole
    -0.07
     ובכל
    -0.06
    ỉnh
    -0.06
     самом
    -0.06
     navigator
    -0.06
    POSITIVE LOGITS
     Etsy
    0.08
    早已
    0.07
    Trying
    0.07
    esti
    0.07
    owy
    0.06
    🏗
    0.06
     Helena
    0.06
    Plans
    0.06
     paddingBottom
    0.06
    土地
    0.06
    Act Density 0.211%

    No Known Activations