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

    Neuronpedia

    INDEX
    Explanations

    official document excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اری
    -0.07
    javascript
    -0.07
    burn
    -0.06
     constitutional
    -0.06
     knees
    -0.06
    STA
    -0.06
     mim
    -0.06
    ovice
    -0.06
    ivist
    -0.06
    Writer
    -0.06
    POSITIVE LOGITS
    .expand
    0.07
    (sentence
    0.06
     cnt
    0.06
    번
    0.06
     Pittsburgh
    0.06
     藤
    0.06
    ользов
    0.06
    щини
    0.06
    �
    0.06
     nejsou
    0.06
    Act Density 0.528%

    No Known Activations