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

    Neuronpedia

    INDEX
    Explanations

    effective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dias
    -0.07
     Wallet
    -0.07
    tiği
    -0.07
    呼ば
    -0.07
     strain
    -0.06
    瀬
    -0.06
    668
    -0.06
     sorter
    -0.06
    |string
    -0.06
    ison
    -0.06
    POSITIVE LOGITS
     click
    0.07
     punitive
    0.07
    \E
    0.06
    Facebook
    0.06
    tainment
    0.06
     assumption
    0.06
    rift
    0.06
     measures
    0.06
     Measures
    0.06
     Upload
    0.06
    Act Density 0.004%

    No Known Activations