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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Named
    -0.08
     Nd
    -0.07
    逯
    -0.07
    _dyn
    -0.07
    些
    -0.07
    🚾
    -0.07
    zyst
    -0.07
     indigenous
    -0.07
     tucked
    -0.06
    ierarchical
    -0.06
    POSITIVE LOGITS
    obe
    0.07
    专线
    0.07
    idding
    0.06
    ////
    0.06
     grav
    0.06
     Loading
    0.06
     Recent
    0.06
    ales
    0.06
     nhấn
    0.06
     shine
    0.06
    Act Density 0.001%

    No Known Activations