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

    Neuronpedia

    INDEX
    Explanations

    using, with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tra
    -0.08
    оте
    -0.07
     maintenant
    -0.07
     readers
    -0.07
    olan
    -0.07
     dust
    -0.07
    uent
    -0.06
    arro
    -0.06
    /rec
    -0.06
    REEN
    -0.06
    POSITIVE LOGITS
    jn
    0.06
     ・
    0.06
    massage
    0.06
    胡
    0.06
    TI
    0.06
    itz
    0.06
     Jinping
    0.06
     Paw
    0.06
    =path
    0.06
       ↵↵
    0.06
    Act Density 0.046%

    No Known Activations