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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tell
    -0.07
    118
    -0.07
     partir
    -0.06
    Datetime
    -0.06
     Арх
    -0.06
    css
    -0.06
     authoritative
    -0.06
    uir
    -0.06
    "But
    -0.06
    “But
    -0.06
    POSITIVE LOGITS
    _tensors
    0.06
    iek
    0.06
    ความค
    0.06
     millet
    0.06
     resembl
    0.06
     XC
    0.06
     incess
    0.06
     ​
    0.06
    _Field
    0.06
    lov
    0.06
    Act Density 0.072%

    No Known Activations