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

    Neuronpedia

    INDEX
    Explanations

    machine parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    都不知道
    -0.08
    вест
    -0.07
     cessation
    -0.07
    resident
    -0.07
    社会化
    -0.07
    )<
    -0.07
    jm
    -0.07
     sunday
    -0.06
     downtime
    -0.06
    ahead
    -0.06
    POSITIVE LOGITS
    .
    0.08
    .lang
    0.08
     templateUrl
    0.07
    Genre
    0.07
    .FromResult
    0.07
    闽
    0.07
     Sic
    0.07
    Offline
    0.06
     scales
    0.06
    toHaveLength
    0.06
    Act Density 0.054%

    No Known Activations