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

    Neuronpedia

    INDEX
    Explanations

    item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اجر
    -0.07
    港
    -0.07
    adır
    -0.07
     вор
    -0.06
    	stack
    -0.06
    mps
    -0.06
    라
    -0.06
    .Export
    -0.06
    ej
    -0.06
     ARR
    -0.06
    POSITIVE LOGITS
     Careers
    0.08
    \M
    0.07
    .LEADING
    0.07
     datos
    0.06
    _kwargs
    0.06
     {-
    0.06
    Identifier
    0.06
     واست
    0.06
     cho
    0.06
     Wings
    0.06
    Act Density 0.003%

    No Known Activations