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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ranges
    -0.06
    带
    -0.06
     Living
    -0.06
    子供
    -0.06
    _ordered
    -0.06
    recipe
    -0.06
    (statearr
    -0.06
     biscuits
    -0.06
     Všech
    -0.06
    Blo
    -0.06
    POSITIVE LOGITS
    اسر
    0.07
    .navigationController
    0.07
    _CT
    0.06
    .Ac
    0.06
    rael
    0.06
     E
    0.06
    	Use
    0.06
    .Σ
    0.06
    르는
    0.06
    _SPE
    0.06
    Act Density 0.032%

    No Known Activations