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

    Neuronpedia

    INDEX
    Explanations

    Costs and prices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itations
    -0.07
    eç
    -0.07
    Built
    -0.07
     Chess
    -0.06
     Layers
    -0.06
    18
    -0.06
     ()
↵
    -0.06
     خص
    -0.06
     felse
    -0.06
     ebook
    -0.06
    POSITIVE LOGITS
     TV
    0.06
     ’
    0.06
     LSM
    0.06
     للإ
    0.06
     veterinary
    0.06
     objedn
    0.06
    .§
    0.06
     oats
    0.06
     tyto
    0.06
    ponce
    0.06
    Act Density 0.063%

    No Known Activations