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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pushed
    -0.08
     revision
    -0.07
     isn
    -0.07
    acman
    -0.07
    ]}
    -0.06
     dislikes
    -0.06
     START
    -0.06
    ㉯
    -0.06
     desn
    -0.06
     Nguyen
    -0.06
    POSITIVE LOGITS
    眼里
    0.07
     IEntity
    0.07
    sole
    0.07
    Adobe
    0.06
    '(
    0.06
    关节
    0.06
    suma
    0.06
    _TestCase
    0.06
    ㅎ
    0.06
    廆
    0.06
    Act Density 0.083%

    No Known Activations