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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detects
    -0.07
    (strategy
    -0.07
    ulin
    -0.06
     skal
    -0.06
     notoriously
    -0.06
    conde
    -0.06
    .Dependency
    -0.06
    ongo
    -0.06
    _DB
    -0.06
     Kral
    -0.06
    POSITIVE LOGITS
    TER
    0.06
    GLenum
    0.06
     GAL
    0.06
    ekyll
    0.06
    InInspector
    0.06
    ter
    0.06
    .sup
    0.06
    uez
    0.06
     ind
    0.06
    ��
    0.06
    Act Density 0.169%

    No Known Activations