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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    英勇
    -0.07
     accused
    -0.07
    AML
    -0.06
     {↵↵↵
    -0.06
    大使
    -0.06
     implicated
    -0.06
    נסיבות
    -0.06
     '\
    -0.06
     consolidate
    -0.06
     commanding
    -0.06
    POSITIVE LOGITS
     Shuttle
    0.07
    ophobia
    0.07
    בי
    0.07
     debating
    0.06
     zwarte
    0.06
    ucks
    0.06
    뻗
    0.06
     Shark
    0.06
    .$.
    0.06
     bait
    0.06
    Act Density 0.003%

    No Known Activations