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

    Neuronpedia

    INDEX
    Explanations

    failed projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vidia
    -0.06
     encoder
    -0.06
     길
    -0.06
     Vendor
    -0.06
    atics
    -0.06
    ATTR
    -0.06
     toen
    -0.06
    рус
    -0.06
    Division
    -0.06
     idiot
    -0.06
    POSITIVE LOGITS
    	back
    0.08
    Mask
    0.07
     záp
    0.07
     Spells
    0.07
    من
    0.06
     sach
    0.06
    	iter
    0.06
    /back
    0.06
     характеристики
    0.06
     seni
    0.06
    Act Density 0.068%

    No Known Activations