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

    Neuronpedia

    INDEX
    Explanations

    Exploit code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Francis
    -0.07
    getType
    -0.07
     classical
    -0.06
     Weiner
    -0.06
     السي
    -0.06
    nis
    -0.06
    ldb
    -0.06
     weary
    -0.06
     Currency
    -0.06
     پا
    -0.06
    POSITIVE LOGITS
    cence
    0.07
    代码
    0.07
     bn
    0.06
     Viet
    0.06
    StrictEqual
    0.06
    ющего
    0.06
     *----------------------------------------------------------------
    0.06
     JSX
    0.06
     calming
    0.06
    
    0.06
    Act Density 0.007%

    No Known Activations