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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divina
    -0.08
    >().
    -0.08
    orra
    -0.07
     richtig
    -0.07
    matched
    -0.07
     inteira
    -0.07
     Oberfläche
    -0.07
     Jangan
    -0.07
     inteiro
    -0.07
    397
    -0.07
    POSITIVE LOGITS
     hereby
    0.10
     sincerely
    0.09
    Introduce
    0.09
     хотел
    0.08
     delighted
    0.08
     Vás
    0.08
     introduces
    0.08
     sincere
    0.08
     Российской
    0.08
     apologize
    0.08
    Act Density 0.014%

    No Known Activations