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

    Neuronpedia

    INDEX
    Explanations

    disclaimer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    概
    -0.07
    弁
    -0.07
     !");↵
    -0.07
    })();
    -0.07
    ("/");↵
    -0.07
    넣
    -0.06
    ῥ
    -0.06
    😨
    -0.06
    -inverse
    -0.06
     });↵
    -0.06
    POSITIVE LOGITS
    .sm
    0.08
    可靠
    0.08
     exquisite
    0.07
    热点
    0.07
     interim
    0.07
    低调
    0.07
     Insights
    0.07
    믜
    0.07
     HM
    0.07
    леп
    0.07
    Act Density 0.001%

    No Known Activations