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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _topic
    -0.07
     BlockPos
    -0.07
    -mf
    -0.07
     yrs
    -0.06
     tek
    -0.06
    apg
    -0.06
     follower
    -0.06
    活动
    -0.06
    협
    -0.06
     созд
    -0.06
    POSITIVE LOGITS
    ━━━━
    0.07
     Reference
    0.07
     churn
    0.07
     folly
    0.06
     Shiite
    0.06
    ستانی
    0.06
     Delay
    0.06
     horse
    0.06
     koy
    0.06
     preventative
    0.06
    Act Density 0.001%

    No Known Activations