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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -----↵
    -0.07
     Female
    -0.07
     Isle
    -0.07
     Languages
    -0.07
     correct
    -0.07
     aware
    -0.06
     pole
    -0.06
     Whilst
    -0.06
    /an
    -0.06
    14
    -0.06
    POSITIVE LOGITS
     mandate
    0.07
    ');");↵
    0.07
     começ
    0.06
     initi
    0.06
    册
    0.06
     inaugur
    0.06
     inici
    0.06
     abroad
    0.06
    ulan
    0.06
    ihil
    0.06
    Act Density 0.018%

    No Known Activations