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

    Neuronpedia

    INDEX
    Explanations

    code using dl4j/nd4j

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Summary
    -0.07
    -machine
    -0.07
    .Dense
    -0.06
     bathrooms
    -0.06
    //**↵
    -0.06
     Drive
    -0.06
     famously
    -0.06
    ViewHolder
    -0.06
     RS
    -0.06
     asserting
    -0.06
    POSITIVE LOGITS
     cria
    0.06
    /api
    0.06
    soever
    0.06
     kapat
    0.06
    liga
    0.06
    .mit
    0.05
     schon
    0.05
     PROC
    0.05
    �
    0.05
     корот
    0.05
    Act Density 0.002%

    No Known Activations