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

    Neuronpedia

    INDEX
    Explanations

    Bu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defining
    -0.06
     revolutions
    -0.06
     early
    -0.06
     titled
    -0.06
     Vườn
    -0.06
    cis
    -0.06
    sorting
    -0.06
     Vig
    -0.06
     perfect
    -0.06
     شورای
    -0.06
    POSITIVE LOGITS
    ζα
    0.07
    ALER
    0.06
    ดร
    0.06
    �
    0.06
     قوان
    0.06
    Order
    0.06
    și
    0.06
    alle
    0.06
     perpet
    0.06
    olare
    0.06
    Act Density 0.004%

    No Known Activations