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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sabe
    -0.07
    optimizer
    -0.07
     ос
    -0.06
    resultado
    -0.06
     Meditation
    -0.06
     رایگان
    -0.06
    iltr
    -0.06
    elsea
    -0.06
     significa
    -0.06
    _callbacks
    -0.06
    POSITIVE LOGITS
     Should
    0.07
    must
    0.07
    [image
    0.07
     ;;↵
    0.06
    Should
    0.06
    -goal
    0.06
     
    0.06
     hafta
    0.06
    Comments
    0.06
     VX
    0.06
    Act Density 0.001%

    No Known Activations