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

    Neuronpedia

    INDEX
    Explanations

    quote requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assassin
    -0.06
    British
    -0.06
    cdot
    -0.06
    .newaxis
    -0.06
    OMB
    -0.06
    elere
    -0.06
     �
    -0.06
     santa
    -0.06
     unusually
    -0.06
    020
    -0.06
    POSITIVE LOGITS
    Segment
    0.06
    PointerException
    0.06
     Grace
    0.06
     increments
    0.06
    segment
    0.06
    packed
    0.06
    	Block
    0.06
    earer
    0.06
     Detection
    0.06
    /Web
    0.06
    Act Density 0.017%

    No Known Activations