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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Memories
    -0.07
    _Cancel
    -0.06
    History
    -0.06
    قدر
    -0.06
     extractor
    -0.06
     λέ
    -0.06
     paddingLeft
    -0.06
     finder
    -0.06
    estro
    -0.06
    UserRole
    -0.06
    POSITIVE LOGITS
    -an
    0.07
     crushed
    0.06
     besides
    0.06
     адміністра
    0.06
    ์ได
    0.06
    lesen
    0.06
     gambling
    0.06
    —you
    0.06
    "/>↵↵
    0.06
    -a
    0.06
    Act Density 0.002%

    No Known Activations