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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sql
    -0.07
    (writer
    -0.07
    	before
    -0.06
     metaData
    -0.06
     yard
    -0.06
     Silver
    -0.06
     дозволя
    -0.06
     Amid
    -0.06
     jestli
    -0.06
    (val
    -0.06
    POSITIVE LOGITS
    0
    0.09
    desk
    0.07
     Keynes
    0.07
    required
    0.07
    athon
    0.06
    orestation
    0.06
    itung
    0.06
    λα
    0.06
    APON
    0.06
    -regexp
    0.06
    Act Density 0.009%

    No Known Activations