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

    Neuronpedia

    INDEX
    Explanations

    lists and code segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     british
    -0.07
    -resources
    -0.07
     jb
    -0.06
    .Action
    -0.06
     çeşit
    -0.06
    lin
    -0.06
    ercise
    -0.06
     rewarding
    -0.06
     Cameras
    -0.06
    poz
    -0.06
    POSITIVE LOGITS
    مان
    0.06
    Length
    0.06
    -pt
    0.06
     Οκ
    0.06
    taboola
    0.06
    topl
    0.06
    .Dock
    0.06
     همراه
    0.06
     accru
    0.06
    _NEAR
    0.06
    Act Density 0.001%

    No Known Activations