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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (vector
    -0.07
    producer
    -0.06
     Heath
    -0.06
    	sum
    -0.06
    _specific
    -0.06
    Selected
    -0.06
    Anything
    -0.06
     lest
    -0.06
     FORM
    -0.06
    TEMPLATE
    -0.06
    POSITIVE LOGITS
    ocked
    0.07
    -speaking
    0.07
    vvm
    0.06
    /widget
    0.06
    осп
    0.06
    .crm
    0.06
     tempList
    0.06
    лика
    0.06
     withObject
    0.06
    िकट
    0.06
    Act Density 0.005%

    No Known Activations