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

    Neuronpedia

    INDEX
    Explanations

    sentence boundary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manière
    -0.08
    Several
    -0.07
     RN
    -0.07
    /button
    -0.07
    арт
    -0.07
     otros
    -0.07
     propaganda
    -0.06
    _quantity
    -0.06
     prudent
    -0.06
     seriousness
    -0.06
    POSITIVE LOGITS
    ">'.
    0.06
     skating
    0.06
    ServiceImpl
    0.06
    797
    0.06
     ------>
    0.06
     '">'
    0.06
    .makedirs
    0.06
     оформ
    0.06
    Aaron
    0.06
     Inflate
    0.06
    Act Density 0.230%

    No Known Activations