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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cert
    -0.06
    uitar
    -0.06
     徒
    -0.06
     次
    -0.06
     edit
    -0.06
    [ix
    -0.06
     دنی
    -0.06
     гот
    -0.06
     continua
    -0.06
    笑
    -0.06
    POSITIVE LOGITS
    egade
    0.07
    rc
    0.07
    Runner
    0.06
    ........................
    0.06
     THREAD
    0.06
    _portfolio
    0.06
     розк
    0.06
    ]=$
    0.06
    .');↵
    0.06
    .thread
    0.06
    Act Density 0.030%

    No Known Activations