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

    Neuronpedia

    INDEX
    Explanations

    Thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ------------------------------------------------
    -0.07
     MART
    -0.07
    Hel
    -0.07
    [].
    -0.07
    unless
    -0.06
     suit
    -0.06
     generous
    -0.06
     ANSW
    -0.06
     ответ
    -0.06
    ########################################################
    -0.06
    POSITIVE LOGITS
     склад
    0.06
     anticipate
    0.06
     Blessed
    0.06
     رشد
    0.06
     assigned
    0.06
    rag
    0.06
    ้อย
    0.06
     constructors
    0.06
     سرو
    0.06
    thinking
    0.06
    Act Density 0.231%

    No Known Activations