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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }↵↵↵↵
    -0.07
    共和
    -0.07
     lame
    -0.07
     зовсім
    -0.07
     쓰
    -0.07
    	fp
    -0.07
    }↵↵↵↵↵↵
    -0.06
    Domain
    -0.06
     ú
    -0.06
    875
    -0.06
    POSITIVE LOGITS
    hai
    0.07
    _Speed
    0.06
    rav
    0.06
     disable
    0.06
    宝
    0.06
    了解
    0.06
    ued
    0.06
    條
    0.06
    rical
    0.06
    MethodInfo
    0.06
    Act Density 0.189%

    No Known Activations