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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "All
    -0.07
     deadliest
    -0.07
    $txt
    -0.06
    外
    -0.06
    	task
    -0.06
     外
    -0.06
     distant
    -0.06
    .addButton
    -0.06
     뒤
    -0.06
     secretive
    -0.06
    POSITIVE LOGITS
    _pot
    0.07
    θηκαν
    0.07
     Lyn
    0.06
     ripped
    0.06
    Ý
    0.06
    ograd
    0.06
     оформ
    0.06
     malaysia
    0.06
    enler
    0.06
    kehr
    0.06
    Act Density 0.052%

    No Known Activations