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

    Neuronpedia

    INDEX
    Explanations

    to or must

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -)
    -0.08
     juvenile
    -0.07
     coffee
    -0.07
     fullName
    -0.07
    -added
    -0.07
    :green
    -0.07
    _aw
    -0.07
     LAB
    -0.06
    -id
    -0.06
     Hollow
    -0.06
    POSITIVE LOGITS
    壞
    0.07
    change
    0.07
    的气息
    0.07
     BOOK
    0.07
    准确性
    0.07
    Sending
    0.07
    [T
    0.06
    thren
    0.06
     noticing
    0.06
     Sadly
    0.06
    Act Density 0.046%

    No Known Activations