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

    Neuronpedia

    INDEX
    Explanations

    rewarding good behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    수
    -0.07
     niên
    -0.07
    Junior
    -0.06
    映
    -0.06
    트
    -0.06
    afc
    -0.06
     zien
    -0.06
    ancing
    -0.06
    .NoError
    -0.06
     Vander
    -0.06
    POSITIVE LOGITS
     aplicación
    0.07
    内容
    0.07
    Definition
    0.06
    suggest
    0.06
     outnumber
    0.06
     dictionary
    0.06
    _person
    0.06
     кли
    0.06
     reasonable
    0.06
     bolest
    0.06
    Act Density 0.018%

    No Known Activations