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

    Neuronpedia

    INDEX
    Explanations

    font-awesome stylesheets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    十六
    -0.07
     apro
    -0.07
    从业
    -0.07
     станов
    -0.07
     advertisement
    -0.07
    |h
    -0.07
     undocumented
    -0.07
     ASF
    -0.07
     cp
    -0.06
     conduit
    -0.06
    POSITIVE LOGITS
    Margin
    0.08
    出て
    0.07
    静
    0.07
     Stevens
    0.07
    .xaxis
    0.07
     Maine
    0.07
    (target
    0.06
    _COLL
    0.06
     macro
    0.06
     değer
    0.06
    Act Density 0.001%

    No Known Activations