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

    Neuronpedia

    INDEX
    Explanations

    antly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertRaises
    -0.06
    _tokens
    -0.06
     días
    -0.06
    ぼ
    -0.06
     đêm
    -0.06
     Ryder
    -0.06
     courtyard
    -0.06
    chos
    -0.06
    ],
↵
    -0.06
    âu
    -0.06
    POSITIVE LOGITS
     착
    0.07
     importantly
    0.07
     inval
    0.07
     Includes
    0.07
     завер
    0.06
     kuv
    0.06
    .User
    0.06
    LC
    0.06
    hasClass
    0.06
     защ
    0.06
    Act Density 0.006%

    No Known Activations