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

    Neuronpedia

    INDEX
    Explanations

    reducing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خدم
    -0.06
     receivers
    -0.06
    援
    -0.06
    alaria
    -0.06
     når
    -0.06
    okers
    -0.06
    prove
    -0.06
     hàm
    -0.06
     یافته
    -0.06
     شده
    -0.06
    POSITIVE LOGITS
    igung
    0.06
    .local
    0.06
     zo
    0.06
     Waterloo
    0.06
     Photographer
    0.06
     synthes
    0.06
    GetX
    0.06
    .nav
    0.06
    .store
    0.06
    getClass
    0.06
    Act Density 0.067%

    No Known Activations