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

    Neuronpedia

    INDEX
    Explanations

    cycle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (":/
    -0.06
    _find
    -0.06
    isinin
    -0.06
     وف
    -0.06
     bids
    -0.06
    Fund
    -0.06
    474
    -0.06
    ную
    -0.06
     enrichment
    -0.06
     Lead
    -0.06
    POSITIVE LOGITS
     motorcycle
    0.16
     motorcycles
    0.13
     Motorcycle
    0.12
     moto
    0.08
    postalcode
    0.08
     Moto
    0.07
     muscle
    0.07
     Stacy
    0.07
     Camel
    0.07
    になり
    0.07
    Act Density 0.003%

    No Known Activations