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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ForeignKey
    -0.06
     Shoe
    -0.06
     más
    -0.06
     Abby
    -0.06
    larındaki
    -0.06
     oz
    -0.06
     chronic
    -0.06
     fy
    -0.06
    他の
    -0.06
    Vac
    -0.06
    POSITIVE LOGITS
    (reinterpret
    0.07
    /prom
    0.07
     somew
    0.07
    AGED
    0.06
     long
    0.06
    :Any
    0.06
     MMO
    0.06
    ,T
    0.06
     instrumental
    0.06
    кус
    0.06
    Act Density 0.021%

    No Known Activations