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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    콥
    -0.07
    וציא
    -0.07
    سطين
    -0.07
     bern
    -0.07
     deck
    -0.07
    (opt
    -0.07
    _command
    -0.06
    ">',↵
    -0.06
     captive
    -0.06
     outf
    -0.06
    POSITIVE LOGITS
     menus
    0.08
    reeNode
    0.07
    dee
    0.07
    ы
    0.07
    DI
    0.07
    沙发
    0.07
    _ENTRY
    0.06
    ность
    0.06
    ثقة
    0.06
    OF
    0.06
    Act Density 0.001%

    No Known Activations