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

    Neuronpedia

    INDEX
    Explanations

    Russell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lugar
    -0.06
     mnist
    -0.06
    公告
    -0.06
    545
    -0.06
    Nullable
    -0.06
    274
    -0.06
     linewidth
    -0.06
     separating
    -0.06
    550
    -0.06
     trajectory
    -0.06
    POSITIVE LOGITS
     Russell
    0.34
    SELL
    0.10
     Sheffield
    0.09
    ffield
    0.08
     Hodg
    0.07
     Carnegie
    0.07
     Interstate
    0.07
    odí
    0.07
    ッ
    0.07
    antas
    0.07
    Act Density 0.001%

    No Known Activations