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

    Neuronpedia

    INDEX
    Explanations

    competed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deputies
    -0.07
    ictions
    -0.07
     inputData
    -0.07
    ccoli
    -0.07
     tapes
    -0.07
     residency
    -0.07
    periences
    -0.07
    .abs
    -0.07
    shared
    -0.07
     peek
    -0.07
    POSITIVE LOGITS
     class
    0.07
     AK
    0.07
    _pr
    0.06
     War
    0.06
     tho
    0.06
    Vol
    0.06
    }/{
    0.06
    この
    0.06
    /light
    0.06
    	dx
    0.06
    Act Density 0.004%

    No Known Activations