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
    bus
    -0.07
    wner
    -0.07
    рач
    -0.07
    layers
    -0.06
    achen
    -0.06
     Laundry
    -0.06
    Phi
    -0.06
    cold
    -0.06
    -qu
    -0.06
    لك
    -0.06
    POSITIVE LOGITS
    _create
    0.06
     XCTestCase
    0.06
    кой
    0.06
     +#+
    0.06
     osg
    0.06
    /Object
    0.06
     науков
    0.06
    ushort
    0.06
    สน
    0.06
    /manual
    0.06
    Act Density 0.000%

    No Known Activations