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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stretch
    -0.07
     Sense
    -0.07
    potential
    -0.06
    constitution
    -0.06
    ForegroundColor
    -0.06
    хів
    -0.06
    fullname
    -0.06
    HideInInspector
    -0.06
    ,-
    -0.06
    ."),
    -0.06
    POSITIVE LOGITS
    .flex
    0.09
     preço
    0.07
    \Persistence
    0.06
     hollow
    0.06
    oard
    0.06
     metod
    0.06
     فيه
    0.06
     Enjoy
    0.06
     otom
    0.06
    .jsx
    0.06
    Act Density 0.174%

    No Known Activations