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

    Neuronpedia

    INDEX
    Explanations

    hyper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gomez
    -0.07
    columns
    -0.07
     Tabs
    -0.07
     obed
    -0.06
     DD
    -0.06
     Gameplay
    -0.06
    ()][
    -0.06
    lw
    -0.06
    Frameworks
    -0.06
    卷
    -0.06
    POSITIVE LOGITS
    Pers
    0.06
     bio
    0.06
     Bi
    0.06
     Decor
    0.06
    257
    0.06
    科
    0.06
     bi
    0.06
    uppies
    0.06
     Рез
    0.06
    ofil
    0.06
    Act Density 0.005%

    No Known Activations