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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Word
    -0.07
     evaluating
    -0.07
     carries
    -0.07
    Dog
    -0.07
     vítěz
    -0.06
     значение
    -0.06
     rendering
    -0.06
     claiming
    -0.06
    .createObject
    -0.06
    اسة
    -0.06
    POSITIVE LOGITS
     XBOOLE
    0.07
     PE
    0.06
     бенз
    0.06
     société
    0.06
    :init
    0.06
    alion
    0.06
     invalidate
    0.06
     Pascal
    0.06
    ोन
    0.06
     CRA
    0.06
    Act Density 0.015%

    No Known Activations