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

    Neuronpedia

    INDEX
    Explanations

    primate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حر
    -0.07
     impuls
    -0.07
     foil
    -0.06
    vidence
    -0.06
    刘
    -0.06
    亮
    -0.06
    _weight
    -0.06
    λόγ
    -0.06
    ░
    -0.06
    _proof
    -0.06
    POSITIVE LOGITS
     yOffset
    0.07
     perpet
    0.07
     kne
    0.06
     newcomer
    0.06
     Mon
    0.06
     graceful
    0.06
    Translatef
    0.06
     impres
    0.06
     {};
↵
    0.06
    mat
    0.06
    Act Density 0.002%

    No Known Activations