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

    Neuronpedia

    INDEX
    Explanations

    escaping problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lik
    -0.07
    ドラ
    -0.06
    mui
    -0.06
     요
    -0.06
     Trem
    -0.06
    刷
    -0.06
     acciones
    -0.06
     сир
    -0.06
    μιο
    -0.06
    疾
    -0.06
    POSITIVE LOGITS
     beard
    0.06
    ute
    0.06
     posix
    0.06
    avou
    0.06
     analog
    0.06
    aceutical
    0.06
     debit
    0.06
     camera
    0.06
     adjustable
    0.06
     savedInstanceState
    0.06
    Act Density 0.037%

    No Known Activations