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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الغرف
    -0.08
    inder
    -0.08
     SimpleName
    -0.08
     ihrem
    -0.07
    巾
    -0.07
     biệt
    -0.07
    ест
    -0.07
    tees
    -0.07
    �
    -0.07
    瀼
    -0.07
    POSITIVE LOGITS
     mocker
    0.07
    -gl
    0.07
     avalia
    0.07
    ﴀ
    0.07
    _avg
    0.07
     Typeface
    0.07
    急于
    0.07
     allergy
    0.07
    izador
    0.06
    vac
    0.06
    Act Density 0.062%

    No Known Activations