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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disaster
    -0.06
     Ο
    -0.06
     Admiral
    -0.06
    would
    -0.06
     Taliban
    -0.06
    टक
    -0.06
     ADHD
    -0.06
    offs
    -0.06
    YRO
    -0.06
    and
    -0.06
    POSITIVE LOGITS
     string
    0.06
    illator
    0.06
    .options
    0.06
    appable
    0.06
    ỗi
    0.06
    Values
    0.06
     فرود
    0.06
    _checkout
    0.06
     force
    0.06
    /errors
    0.06
    Act Density 0.008%

    No Known Activations