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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trys
    -0.06
    .Does
    -0.06
    _rooms
    -0.06
    ()));
↵
    -0.06
    inned
    -0.06
     оп
    -0.06
    (ep
    -0.06
    む
    -0.06
    -operator
    -0.06
    _stock
    -0.06
    POSITIVE LOGITS
     minors
    0.07
     Metropolitan
    0.06
     آمریک
    0.06
     phil
    0.06
     forecasts
    0.06
     improbable
    0.06
     unreliable
    0.06
     graduate
    0.06
     العربية
    0.06
     crossed
    0.06
    Act Density 0.025%

    No Known Activations