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

    Neuronpedia

    INDEX
    Explanations

    mx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    freeze
    -0.07
    MSG
    -0.07
    _digest
    -0.07
    ,response
    -0.07
    &&(
    -0.07
     numa
    -0.07
     giorn
    -0.07
    @NgModule
    -0.07
     TERMS
    -0.07
    TOT
    -0.07
    POSITIVE LOGITS
    :\
    0.08
    iders
    0.07
    许可证
    0.07
     MX
    0.07
    苹果
    0.06
    anes
    0.06
     "..
    0.06
    ites
    0.06
    묽
    0.06
     plaque
    0.06
    Act Density 0.003%

    No Known Activations