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

    Neuronpedia

    INDEX
    Explanations

    Care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Richmond
    -0.07
    ewriter
    -0.06
    962
    -0.06
    Purple
    -0.06
    [Y
    -0.06
     reasonable
    -0.06
     succeed
    -0.06
     Metal
    -0.06
    090
    -0.06
     MONEY
    -0.06
    POSITIVE LOGITS
    adaş
    0.07
     креп
    0.06
     primera
    0.06
     DU
    0.06
     رسید
    0.06
     recep
    0.06
     μεγ
    0.06
     pornstar
    0.06
     Einsatz
    0.06
    aintenance
    0.06
    Act Density 0.009%

    No Known Activations