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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loan
    -0.07
    ณฑ
    -0.07
     �
    -0.07
    Portland
    -0.07
    MySQL
    -0.06
    expects
    -0.06
    optimized
    -0.06
    姑
    -0.06
    uncan
    -0.06
     subsidies
    -0.06
    POSITIVE LOGITS
    -tabs
    0.06
     té
    0.06
    (ex
    0.06
     Decomp
    0.06
     separat
    0.06
     إليه
    0.06
     enticing
    0.06
    figures
    0.06
    log
    0.06
    Radius
    0.06
    Act Density 0.014%

    No Known Activations