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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infinite
    -0.07
    alaxy
    -0.07
     중
    -0.06
     possessing
    -0.06
     раздел
    -0.06
    gree
    -0.06
     цель
    -0.06
    .STRING
    -0.06
    �
    -0.06
    .pt
    -0.06
    POSITIVE LOGITS
    ock
    0.07
     InternalEnumerator
    0.07
    FUL
    0.07
    Future
    0.06
     uprav
    0.06
    ,['
    0.06
     disregard
    0.06
    동안
    0.06
     Feng
    0.06
     unfairly
    0.06
    Act Density 0.002%

    No Known Activations