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

    Neuronpedia

    INDEX
    Explanations

    Layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laser
    -0.07
     stri
    -0.07
     Jer
    -0.07
     Sar
    -0.07
     Hence
    -0.07
     give
    -0.06
     Gim
    -0.06
    Intensity
    -0.06
    _ter
    -0.06
    positive
    -0.06
    POSITIVE LOGITS
     NaN
    0.10
    Layout
    0.08
     Layout
    0.08
    NaN
    0.07
     Outputs
    0.07
     Analyst
    0.06
    다가
    0.06
    ographs
    0.06
    ']):↵
    0.06
    RESH
    0.06
    Act Density 0.001%

    No Known Activations