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

    Neuronpedia

    INDEX
    Explanations

    being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engulf
    -0.06
    .**************
    -0.06
    EC
    -0.06
    -Cs
    -0.06
    .dt
    -0.06
    xFA
    -0.06
    Ec
    -0.05
    Entre
    -0.05
     sour
    -0.05
    }))↵↵
    -0.05
    POSITIVE LOGITS
     tục
    0.08
     дека
    0.08
     Tweet
    0.07
     Bills
    0.07
    له
    0.07
     MID
    0.07
     Updating
    0.06
     arrow
    0.06
     catalogs
    0.06
    虑
    0.06
    Act Density 0.031%

    No Known Activations