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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talk
    -0.07
     málo
    -0.07
     Aren
    -0.07
    _dir
    -0.07
    Users
    -0.07
     cropped
    -0.06
     Have
    -0.06
    .node
    -0.06
     Joan
    -0.06
    Rights
    -0.06
    POSITIVE LOGITS
    idf
    0.07
    oxid
    0.06
    _calibration
    0.06
    timeline
    0.06
    sprintf
    0.06
    住宅
    0.06
     wartime
    0.06
     RAW
    0.06
     Arial
    0.06
     vým
    0.06
    Act Density 0.042%

    No Known Activations