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

    Neuronpedia

    INDEX
    Explanations

    People's Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sights
    -0.07
    称
    -0.06
    мін
    -0.06
     lxml
    -0.06
    既然
    -0.06
    ilere
    -0.06
    吉
    -0.06
    496
    -0.06
    Handlers
    -0.06
     Owen
    -0.06
    POSITIVE LOGITS
    _WAIT
    0.07
    稳
    0.06
     anom
    0.06
     oat
    0.06
     Establish
    0.06
     strm
    0.06
     nood
    0.06
     effectiveness
    0.06
    oze
    0.06
     bacheca
    0.06
    Act Density 0.020%

    No Known Activations