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

    Neuronpedia

    INDEX
    Explanations

    software file structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stainless
    -0.07
    -HT
    -0.07
     stopped
    -0.06
    Comm
    -0.06
    ключ
    -0.06
    Six
    -0.06
     WTO
    -0.06
     Teknik
    -0.06
    Disp
    -0.06
     strained
    -0.06
    POSITIVE LOGITS
    anner
    0.07
    ignite
    0.06
    دة
    0.06
     poder
    0.06
     Василь
    0.06
     înt
    0.06
     bride
    0.06
     Tennessee
    0.06
     Можно
    0.06
    addGap
    0.06
    Act Density 0.015%

    No Known Activations