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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蕈
    -0.08
     gangs
    -0.07
     traf
    -0.07
    igi
    -0.07
     TTC
    -0.07
    Reward
    -0.07
     walmart
    -0.07
     sings
    -0.07
    _chart
    -0.07
    电量
    -0.07
    POSITIVE LOGITS
     departure
    0.08
     distinct
    0.07
     Dry
    0.07
    水平
    0.07
    Throwable
    0.07
    .).
    0.07
     Stream
    0.07
    ющий
    0.07
    ilateral
    0.07
    .']
    0.07
    Act Density 0.000%

    No Known Activations