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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nin
    -0.06
     zá
    -0.06
    .questions
    -0.06
    goals
    -0.06
    ARY
    -0.06
     шах
    -0.06
     Antar
    -0.06
    /********
    -0.06
     flank
    -0.06
     lâu
    -0.06
    POSITIVE LOGITS
    "bytes
    0.08
     legally
    0.08
    piece
    0.07
     dü
    0.07
    =UTF
    0.07
    "url
    0.06
    öffent
    0.06
    -setting
    0.06
    veal
    0.06
    viewer
    0.06
    Act Density 0.036%

    No Known Activations