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

    Neuronpedia

    INDEX
    Explanations

    ']['

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    j
    -0.08
    supports
    -0.07
    sus
    -0.07
    duction
    -0.07
     urge
    -0.07
     instrument
    -0.07
     tug
    -0.07
    祖
    -0.07
    deleted
    -0.07
    asury
    -0.07
    POSITIVE LOGITS
    另一个
    0.08
    EmptyEntries
    0.08
    Endpoint
    0.08
     excluding
    0.07
    (outfile
    0.07
    죗
    0.07
    �
    0.07
    Beer
    0.07
    _GOOD
    0.07
     hobbies
    0.07
    Act Density 0.002%

    No Known Activations