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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AQ
    -0.06
     accordingly
    -0.06
     altern
    -0.06
     pla
    -0.06
     Even
    -0.06
     communicated
    -0.06
    _route
    -0.06
     Again
    -0.06
    ศจ
    -0.06
     Hp
    -0.06
    POSITIVE LOGITS
    igslist
    0.07
     XM
    0.07
    ์บ
    0.06
     그런
    0.06
    Topology
    0.06
    дии
    0.06
     bothered
    0.06
     Một
    0.06
     Sleeve
    0.06
    ordan
    0.06
    Act Density 0.002%

    No Known Activations