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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있는
    -0.08
    logen
    -0.07
    ために
    -0.07
    创建
    -0.07
     있어
    -0.07
     rele
    -0.06
    ivism
    -0.06
     seeker
    -0.06
    lee
    -0.06
    )];
↵
    -0.06
    POSITIVE LOGITS
     Unary
    0.07
     attracted
    0.07
    atat
    0.07
    нима
    0.07
     Dynamo
    0.07
     ensures
    0.06
    핑
    0.06
     AudioSource
    0.06
     fi
    0.06
    Discount
    0.06
    Act Density 0.011%

    No Known Activations