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

    Neuronpedia

    INDEX
    Explanations

    expressing thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一個
    -0.06
    encies
    -0.06
     votes
    -0.06
    .aw
    -0.06
    ляти
    -0.06
     leaving
    -0.06
     embed
    -0.06
    resolver
    -0.06
     dị
    -0.06
     другого
    -0.06
    POSITIVE LOGITS
     QLabel
    0.07
     Cot
    0.06
    _VERBOSE
    0.06
    ,content
    0.06
     assertFalse
    0.06
    }`).
    0.06
     plaintext
    0.06
     *)&
    0.06
    ]._
    0.06
     UInt
    0.06
    Act Density 0.259%

    No Known Activations