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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’re
    -0.07
     eclipse
    -0.07
     consulting
    -0.07
     Cove
    -0.07
    trans
    -0.07
    umu
    -0.07
    Core
    -0.06
     Card
    -0.06
     Rod
    -0.06
    Plane
    -0.06
    POSITIVE LOGITS
    .***.***
    0.07
     кош
    0.06
     đặt
    0.06
    .pid
    0.06
     تصميم
    0.06
    -google
    0.06
    acje
    0.06
     childish
    0.06
    _maker
    0.06
    >↵↵↵
    0.06
    Act Density 0.075%

    No Known Activations