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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vect
    -0.07
    KV
    -0.06
     riders
    -0.06
     intro
    -0.06
     MU
    -0.06
    -making
    -0.06
     Trophy
    -0.06
    [o
    -0.06
    [#
    -0.06
     torn
    -0.06
    POSITIVE LOGITS
     Depending
    0.06
    urg
    0.06
    ’є
    0.06
    urate
    0.06
     extraordinary
    0.06
    มนตร
    0.06
    erialize
    0.06
     волос
    0.06
     stylesheet
    0.06
     Bab
    0.06
    Act Density 0.040%

    No Known Activations