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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    等方面的
    -0.07
    沦为
    -0.07
     hayatını
    -0.07
    俾
    -0.07
    硍
    -0.07
     проблем
    -0.07
     sinon
    -0.06
     рест
    -0.06
     ils
    -0.06
     defended
    -0.06
    POSITIVE LOGITS
    说着
    0.06
     }}">↵
    0.06
    ⟨
    0.06
    courses
    0.06
    ACKET
    0.06
    .Experimental
    0.06
     Люб
    0.06
    Sortable
    0.06
     forks
    0.06
    缺
    0.06
    Act Density 0.011%

    No Known Activations