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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jam
    -0.07
    bay
    -0.07
    	diff
    -0.06
    ian
    -0.06
     Walters
    -0.06
     superiority
    -0.06
     goodbye
    -0.06
    ('./
    -0.06
    getObject
    -0.06
     rq
    -0.06
    POSITIVE LOGITS
     Hermes
    0.08
    etal
    0.07
     Neighborhood
    0.06
    /change
    0.06
    /cloud
    0.06
    (async
    0.06
     Consum
    0.06
     astr
    0.06
     ἐ
    0.06
    EST
    0.06
    Act Density 0.001%

    No Known Activations