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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rahul
    -0.07
    \Builder
    -0.06
     WR
    -0.06
     Bris
    -0.06
     Wend
    -0.06
    782
    -0.05
     \$
    -0.05
    .uf
    -0.05
    _ON
    -0.05
     Ts
    -0.05
    POSITIVE LOGITS
    crire
    0.07
    arking
    0.07
    piration
    0.07
    クション
    0.07
     CGSize
    0.07
     withstand
    0.07
    INARY
    0.07
     mantle
    0.06
    」，
    0.06
    urdy
    0.06
    Act Density 0.002%

    No Known Activations