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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Post
    -0.07
    ReturnValue
    -0.06
    #
    -0.06
     //#
    -0.06
     Ford
    -0.06
    ‌پ
    -0.06
    Media
    -0.06
    urus
    -0.06
    quis
    -0.06
    ories
    -0.06
    POSITIVE LOGITS
     TILE
    0.07
     sympathetic
    0.07
    旁
    0.07
     akin
    0.06
     reactionary
    0.06
    140
    0.06
    ندگی
    0.06
     próximo
    0.06
    کاری
    0.06
    ianne
    0.06
    Act Density 0.004%

    No Known Activations