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

    Neuronpedia

    INDEX
    Explanations

    Corporate responsibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，如果
    -0.07
    ILTER
    -0.07
    MENT
    -0.06
    atement
    -0.06
    项
    -0.06
    лот
    -0.06
    зації
    -0.06
    итом
    -0.06
    ział
    -0.06
    avourite
    -0.06
    POSITIVE LOGITS
     sonucu
    0.07
    átel
    0.07
     пла
    0.06
     sample
    0.06
    _er
    0.06
    _beta
    0.06
    coded
    0.06
    .SaveChanges
    0.06
     poll
    0.06
    .Rollback
    0.06
    Act Density 0.064%

    No Known Activations