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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    javascript
    -0.08
     score
    -0.08
    .update
    -0.07
     photographs
    -0.07
     Dahl
    -0.07
     Hulu
    -0.07
     flag
    -0.07
    likes
    -0.07
    status
    -0.06
     cleanup
    -0.06
    POSITIVE LOGITS
    纯
    0.07
    ерш
    0.07
    �
    0.06
     pesso
    0.06
    .filename
    0.06
     приня
    0.06
    焼
    0.06
    .Filters
    0.06
    .cancel
    0.06
    ुजर
    0.06
    Act Density 0.013%

    No Known Activations