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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zor
    -0.07
     如果
    -0.06
     yc
    -0.06
    '])
↵
    -0.06
     koş
    -0.06
     mirac
    -0.06
     bus
    -0.06
    taj
    -0.06
     oci
    -0.06
    าอย
    -0.06
    POSITIVE LOGITS
     Observer
    0.07
     perv
    0.07
    reater
    0.07
    _log
    0.06
     graphical
    0.06
     Fors
    0.06
     Disc
    0.06
     SSL
    0.06
     Welt
    0.06
     Bakery
    0.06
    Act Density 0.000%

    No Known Activations