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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gs
    -0.07
     würde
    -0.07
    hek
    -0.07
    ген
    -0.06
    ITEM
    -0.06
    avery
    -0.06
     annonces
    -0.06
     spectral
    -0.06
     nc
    -0.06
    heads
    -0.06
    POSITIVE LOGITS
    对象
    0.07
     Stephen
    0.07
     SECRET
    0.06
     Elvis
    0.06
    ##↵↵
    0.06
     Buddy
    0.06
    awn
    0.06
     interior
    0.06
    `)↵
    0.06
     bearer
    0.06
    Act Density 0.003%

    No Known Activations