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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    มากกว
    -0.07
     موتور
    -0.07
     avere
    -0.06
    -feed
    -0.06
    Closed
    -0.06
    :")
    -0.06
    Dummy
    -0.06
     Better
    -0.06
    lernen
    -0.06
     그리
    -0.06
    POSITIVE LOGITS
     urging
    0.06
     grads
    0.06
     Roads
    0.06
    	property
    0.06
     reperc
    0.06
    filer
    0.06
    wp
    0.06
     Business
    0.06
     Collections
    0.06
    çe
    0.06
    Act Density 0.050%

    No Known Activations