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

    Neuronpedia

    INDEX
    Explanations

    -team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prima
    -0.07
    _expect
    -0.07
     geometry
    -0.07
    érie
    -0.06
    _focus
    -0.06
    locked
    -0.06
    UCKET
    -0.06
     Purpose
    -0.06
     ngủ
    -0.06
    子供
    -0.06
    POSITIVE LOGITS
     трав
    0.07
    IGNED
    0.06
     perg
    0.06
     trespass
    0.06
    dated
    0.06
    /change
    0.06
    .getValueAt
    0.06
     Wrong
    0.06
     giờ
    0.06
     کمک
    0.06
    Act Density 0.001%

    No Known Activations