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

    Neuronpedia

    INDEX
    Explanations

    scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     astronauts
    -0.07
     assistant
    -0.06
     Pais
    -0.06
     Correct
    -0.06
    _editor
    -0.06
     cops
    -0.06
     commend
    -0.06
    技
    -0.06
     Amend
    -0.06
     Lost
    -0.06
    POSITIVE LOGITS
    .eng
    0.07
    readcrumb
    0.07
    APSHOT
    0.06
    	filename
    0.06
     propane
    0.06
     můžete
    0.06
     правила
    0.06
     groupId
    0.06
    "crypto
    0.06
    년에는
    0.06
    Act Density 0.014%

    No Known Activations