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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BİL
    -0.06
    _ipc
    -0.06
     нею
    -0.06
    ojis
    -0.06
    _assignment
    -0.06
    ayah
    -0.06
    ่วย
    -0.06
    /drivers
    -0.06
     вплив
    -0.06
     평
    -0.06
    POSITIVE LOGITS
     generator
    0.07
     mortgages
    0.07
    Returns
    0.07
    RODUCTION
    0.07
     University
    0.07
    _notice
    0.07
     Packers
    0.07
    	bytes
    0.07
    Kom
    0.06
     magnets
    0.06
    Act Density 0.002%

    No Known Activations