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

    Neuronpedia

    INDEX
    Explanations

    from/than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /ar
    -0.06
    Dog
    -0.06
    ства
    -0.06
    iom
    -0.06
    Pot
    -0.06
    虽然
    -0.06
     Growth
    -0.06
    background
    -0.06
    abin
    -0.06
    ریان
    -0.06
    POSITIVE LOGITS
    ACL
    0.08
    \x
    0.07
     zaw
    0.07
     Tories
    0.07
    -api
    0.06
     Setter
    0.06
     hlas
    0.06
     klin
    0.06
    _USE
    0.06
     ◑
    0.06
    Act Density 0.122%

    No Known Activations