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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     example
    -0.08
     JDK
    -0.07
     Could
    -0.06
     entertaining
    -0.06
    Mob
    -0.06
    -ts
    -0.06
    _space
    -0.06
     văn
    -0.06
    опас
    -0.06
    uges
    -0.06
    POSITIVE LOGITS
     кора
    0.07
     nltk
    0.06
     Laurel
    0.06
     He
    0.06
     '''
↵
    0.06
     he
    0.06
     автом
    0.06
    งข
    0.06
     Oliveira
    0.06
     %{
    0.06
    Act Density 0.013%

    No Known Activations