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

    Neuronpedia

    INDEX
    Explanations

    hardware configuration code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ist
    -0.08
     сто
    -0.07
     silk
    -0.07
    $I
    -0.07
     exter
    -0.06
    ैन
    -0.06
     enforced
    -0.06
    PD
    -0.06
    ayne
    -0.06
    _draft
    -0.06
    POSITIVE LOGITS
    Transactions
    0.07
    净
    0.06
    ῆς
    0.06
    family
    0.06
    Fantastic
    0.06
     animations
    0.06
    >"+↵
    0.06
    ustralian
    0.06
    rance
    0.06
    ~~~~~~~~~~~~~~~~
    0.06
    Act Density 0.010%

    No Known Activations