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

    Neuronpedia

    INDEX
    Explanations

    locations or organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dependence
    -0.06
    Independent
    -0.06
    Info
    -0.06
    (Adapter
    -0.06
     polymer
    -0.06
    Planning
    -0.06
    _output
    -0.06
     conversions
    -0.06
     configs
    -0.06
     Planning
    -0.06
    POSITIVE LOGITS
     "$(
    0.08
     dood
    0.07
     그것
    0.07
     ($(
    0.07
    idd
    0.07
     بالا
    0.07
     handleSubmit
    0.07
     endforeach
    0.06
     Read
    0.06
    ...)
    0.06
    Act Density 0.032%

    No Known Activations