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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonded
    -0.08
    -В
    -0.07
    пра
    -0.06
    zem
    -0.06
     Joey
    -0.06
     writer
    -0.06
    得到
    -0.06
     سع
    -0.06
    tpl
    -0.06
    <Pair
    -0.06
    POSITIVE LOGITS
    _REMOVE
    0.07
    	mysqli
    0.07
     notifying
    0.06
     куб
    0.06
     hizmeti
    0.06
     inscription
    0.06
     vandalism
    0.06
    ******
    0.06
    |int
    0.06
    iştir
    0.06
    Act Density 0.013%

    No Known Activations