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

    Neuronpedia

    INDEX
    Explanations

    Conversational filler, interjections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shields
    -0.06
     иметь
    -0.06
    Have
    -0.06
    	false
    -0.06
      ↵↵↵
    -0.06
    "}↵↵
    -0.06
     Evidence
    -0.06
     MORE
    -0.06
    GREEN
    -0.06
     вересня
    -0.06
    POSITIVE LOGITS
     raj
    0.07
    .ll
    0.07
    carry
    0.06
     뛰
    0.06
    .CLIENT
    0.06
    _finish
    0.06
    matplotlib
    0.06
     Owl
    0.06
    toJson
    0.06
    -Semitism
    0.06
    Act Density 0.055%

    No Known Activations