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

    Neuronpedia

    INDEX
    Explanations

    Computer processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	TRACE
    -0.08
    _iff
    -0.07
    	value
    -0.07
    _recipe
    -0.07
    _main
    -0.07
     Spirits
    -0.07
     Euler
    -0.06
    /pdf
    -0.06
    	Destroy
    -0.06
     capitalist
    -0.06
    POSITIVE LOGITS
     arrayOf
    0.06
    .parent
    0.06
    ocker
    0.06
     likes
    0.06
     Laptop
    0.06
     swift
    0.06
     tụ
    0.05
    ominator
    0.05
    を開
    0.05
     mutated
    0.05
    Act Density 0.134%

    No Known Activations