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

    Neuronpedia

    INDEX
    Explanations

    Fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OPER
    -0.06
     Федера
    -0.06
    스를
    -0.06
    卢
    -0.06
    sit
    -0.06
     років
    -0.06
    -д
    -0.06
    getC
    -0.06
     sagte
    -0.06
     mét
    -0.06
    POSITIVE LOGITS
    .setBorder
    0.07
    이며
    0.07
     MK
    0.06
    勤
    0.06
     prominent
    0.06
    -catching
    0.06
     ทาง
    0.06
    _suspend
    0.06
    _primitive
    0.06
    -phone
    0.06
    Act Density 0.001%

    No Known Activations