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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capacities
    -0.07
    ('_
    -0.06
    CharacterSet
    -0.06
    ]]
    -0.06
     želez
    -0.06
     Force
    -0.06
     ancestors
    -0.06
    "])
    -0.06
    middlewares
    -0.06
     Supports
    -0.06
    POSITIVE LOGITS
     그녀는
    0.07
     bout
    0.07
    sbin
    0.07
     sprint
    0.06
    ictureBox
    0.06
    rowser
    0.06
    asic
    0.06
     эту
    0.06
     cosmos
    0.06
    仪
    0.06
    Act Density 0.008%

    No Known Activations