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

    Neuronpedia

    INDEX
    Explanations

    Calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ví
    -0.08
     Pierce
    -0.07
     carrying
    -0.07
     Carrie
    -0.07
     honda
    -0.07
     akka
    -0.07
     comerc
    -0.07
     succesfully
    -0.06
    aisal
    -0.06
     практичес
    -0.06
    POSITIVE LOGITS
    좁
    0.07
    מפ
    0.07
    _Base
    0.07
    .container
    0.06
    фт
    0.06
    쩰
    0.06
    reach
    0.06
    Alloc
    0.06
    鲍
    0.06
     allegations
    0.06
    Act Density 0.006%

    No Known Activations