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

    Neuronpedia

    INDEX
    Explanations

    opinions, advice, negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apest
    -0.07
     Marines
    -0.07
    CAF
    -0.07
     uniq
    -0.07
     Canadiens
    -0.07
    פרס
    -0.07
    👮
    -0.07
    携程
    -0.07
    ListNode
    -0.06
    .sprite
    -0.06
    POSITIVE LOGITS
     Ready
    0.08
    .oper
    0.08
    不够
    0.08
     -------
    0.07
     Ordinary
    0.07
    寓
    0.07
    DAL
    0.07
    宇
    0.07
     origin
    0.07
    utation
    0.07
    Act Density 0.107%

    No Known Activations