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

    Neuronpedia

    INDEX
    Explanations

    un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     famed
    -0.08
    腾
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.07
     Nate
    -0.06
     各
    -0.06
    PGA
    -0.06
    _dicts
    -0.06
    SX
    -0.06
    TK
    -0.06
     Sew
    -0.06
    POSITIVE LOGITS
     un
    0.11
     Un
    0.07
     juices
    0.07
    ẫn
    0.06
     Unblock
    0.06
    ían
    0.06
     extingu
    0.06
     uns
    0.06
    ύν
    0.06
     irritated
    0.06
    Act Density 0.030%

    No Known Activations