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

    Neuronpedia

    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atron
    -0.07
    .Microsoft
    -0.07
    乎
    -0.06
     य
    -0.06
     chatter
    -0.06
    oton
    -0.06
     friday
    -0.06
    메
    -0.06
    нє
    -0.06
     eggs
    -0.06
    POSITIVE LOGITS
    :[↵
    0.07
    ected
    0.06
    _COUNTRY
    0.06
    jsp
    0.06
     �
    0.06
     incentive
    0.06
    [args
    0.06
    (nullable
    0.06
     storing
    0.06
    ーニ
    0.06
    Act Density 0.072%

    No Known Activations