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

    Neuronpedia

    INDEX
    Explanations

    #!

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loving
    -0.08
     Var
    -0.08
    텣
    -0.08
    评审
    -0.07
    	dt
    -0.07
     Fighters
    -0.07
     sec
    -0.07
     pra
    -0.07
     tends
    -0.07
    ived
    -0.07
    POSITIVE LOGITS
    .Apply
    0.08
    ьте
    0.07
    Yep
    0.07
    ﹃
    0.07
    تطوير
    0.07
    CppGuid
    0.07
    得天独
    0.07
    مفهوم
    0.06
    镩
    0.06
    ᄐ
    0.06
    Act Density 0.000%

    No Known Activations