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

    Neuronpedia

    INDEX
    Explanations

    Average/Rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diagnosed
    -0.06
    sq
    -0.06
     suing
    -0.06
     реє
    -0.06
     Alex
    -0.06
     polled
    -0.06
     spouses
    -0.06
    -track
    -0.06
     shapes
    -0.06
    “The
    -0.06
    POSITIVE LOGITS
    Normals
    0.07
     ferment
    0.07
    _coef
    0.06
    ội
    0.06
    597
    0.06
    icemail
    0.06
     waypoints
    0.06
    _LAYER
    0.06
    odel
    0.06
    真是
    0.06
    Act Density 0.007%

    No Known Activations