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

    Neuronpedia

    INDEX
    Explanations

    Falls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Om
    -0.08
    19
    -0.07
    mam
    -0.07
    21
    -0.07
    12
    -0.07
    Desde
    -0.06
     kimse
    -0.06
    	comment
    -0.06
    ,index
    -0.06
    .account
    -0.06
    POSITIVE LOGITS
    инки
    0.07
    HeadersHeight
    0.06
     τέ
    0.06
    POCH
    0.06
     وی
    0.06
    $GLOBALS
    0.06
    аб
    0.06
    集
    0.06
    婚
    0.06
    uset
    0.06
    Act Density 0.087%

    No Known Activations