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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Types
    -0.07
     đây
    -0.07
    北斗
    -0.07
    邠
    -0.07
     Comb
    -0.07
    forum
    -0.07
     because
    -0.07
     Rel
    -0.06
    犏
    -0.06
     elem
    -0.06
    POSITIVE LOGITS
    :";
↵
    0.07
    篮板
    0.07
    ouncements
    0.07
     Blob
    0.07
    )new
    0.06
     redemption
    0.06
    production
    0.06
     squad
    0.06
    ,class
    0.06
     apartments
    0.06
    Act Density 0.002%

    No Known Activations