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

    Neuronpedia

    INDEX
    Explanations

    uid or Druid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ƀ
    -0.08
    .age
    -0.07
    rocess
    -0.07
    Licensed
    -0.07
    national
    -0.07
     prince
    -0.07
    [action
    -0.07
    .Offset
    -0.06
     more
    -0.06
     Roma
    -0.06
    POSITIVE LOGITS
    룻
    0.08
     перев
    0.07
    テレビ
    0.07
    ::~
    0.06
     GW
    0.06
     ByteArray
    0.06
     terug
    0.06
     outcry
    0.06
     geen
    0.06
    .amazonaws
    0.06
    Act Density 0.001%

    No Known Activations