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
    jump
    -0.07
     angl
    -0.06
    	Size
    -0.06
     دختر
    -0.06
     قرار
    -0.06
     Jer
    -0.06
    screens
    -0.06
    proxy
    -0.06
     throwError
    -0.06
     Laundry
    -0.06
    POSITIVE LOGITS
    ้น
    0.06
    vant
    0.06
     consequential
    0.06
    _compile
    0.06
     nutné
    0.06
    softmax
    0.06
    _soft
    0.06
     تعریف
    0.06
     인기
    0.06
    Mc
    0.06
    Act Density 0.019%

    No Known Activations