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

    Neuronpedia

    INDEX
    Explanations

    general english language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Buscar
    -0.06
     jury
    -0.06
    асс
    -0.06
    wie
    -0.06
    	pl
    -0.06
    .food
    -0.06
    ertino
    -0.05
     �
    -0.05
    梯
    -0.05
    roof
    -0.05
    POSITIVE LOGITS
    metatable
    0.07
    -content
    0.07
     InputDecoration
    0.06
     trimming
    0.06
     squared
    0.06
    년도
    0.06
    -quote
    0.06
    TargetException
    0.06
    _INST
    0.06
    \data
    0.06
    Act Density 3.196%

    No Known Activations