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

    Neuronpedia

    INDEX
    Explanations

    extract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     điều
    -0.07
     Sala
    -0.07
    tolower
    -0.07
    mousedown
    -0.07
     وما
    -0.06
     Ober
    -0.06
    Risk
    -0.06
     skew
    -0.06
    lifetime
    -0.06
     apprentice
    -0.06
    POSITIVE LOGITS
     glyc
    0.06
     Serving
    0.06
     qualify
    0.06
    (comb
    0.06
     inFile
    0.06
     hybrid
    0.06
    )::
    0.06
    스의
    0.06
    jf
    0.06
    isting
    0.06
    Act Density 0.013%

    No Known Activations