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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clid
    -0.06
     七
    -0.06
    Roger
    -0.06
     ν
    -0.06
     appealed
    -0.06
     Moore
    -0.06
    _ar
    -0.06
    pv
    -0.06
     Heaven
    -0.06
    xr
    -0.06
    POSITIVE LOGITS
    _REFERER
    0.07
     редак
    0.07
     bör
    0.06
     바람
    0.06
     کمتر
    0.06
     مرکز
    0.06
    (action
    0.06
     osp
    0.06
     episode
    0.06
     Kardash
    0.06
    Act Density 0.011%

    No Known Activations