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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     database
    -0.08
    ropolis
    -0.07
     ourselves
    -0.07
     struck
    -0.07
     airplanes
    -0.06
    ','#
    -0.06
     historian
    -0.06
    ↵    ↵
    -0.06
     critic
    -0.06
     secured
    -0.06
    POSITIVE LOGITS
    ευ
    0.07
     блю
    0.06
     sightings
    0.06
    wal
    0.06
    ày
    0.06
    668
    0.06
    amaha
    0.06
    ουν
    0.06
     destinationViewController
    0.06
     було
    0.06
    Act Density 0.060%

    No Known Activations