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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ierre
    -0.07
     Và
    -0.07
    :])↵
    -0.06
     greetings
    -0.06
    슨
    -0.06
    ิลล
    -0.06
    andFilterWhere
    -0.06
    undan
    -0.06
    彼
    -0.06
     sağlayan
    -0.06
    POSITIVE LOGITS
     Bea
    0.06
     pub
    0.06
    publisher
    0.06
     JText
    0.06
    龍
    0.06
    tex
    0.06
    hist
    0.06
    �
    0.06
     Kop
    0.06
    .createTextNode
    0.06
    Act Density 0.031%

    No Known Activations