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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facilement
    -0.08
    ran
    -0.08
    angu
    -0.08
     regularly
    -0.07
     frequently
    -0.07
     Bosnia
    -0.07
     간
    -0.07
    )));
    -0.07
     étudi
    -0.07
     lorsque
    -0.07
    POSITIVE LOGITS
     wants
    0.11
     Wants
    0.10
     хочет
    0.10
     хотите
    0.09
     يريد
    0.09
     זה
    0.09
    Uw
    0.09
     requisitos
    0.08
     хотят
    0.08
     चाहता
    0.08
    Act Density 0.022%

    No Known Activations