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

    Neuronpedia

    INDEX
    Explanations

    TH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^^
    -0.07
     Ry
    -0.07
    海
    -0.06
     C
    -0.06
    луч
    -0.06
    AQ
    -0.06
     alloys
    -0.06
    .Push
    -0.06
     Pr
    -0.06
     views
    -0.06
    POSITIVE LOGITS
    32
    0.07
     Transitional
    0.07
    udson
    0.06
     archived
    0.06
    OFF
    0.06
     GUIDE
    0.06
     perform
    0.06
     veterinarian
    0.06
    icester
    0.06
    dep
    0.06
    Act Density 0.001%

    No Known Activations