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

    Neuronpedia

    INDEX
    Explanations

    last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fibonacci
    -0.07
     steep
    -0.07
     Ritual
    -0.07
     separator
    -0.06
    /API
    -0.06
    als
    -0.06
    eries
    -0.06
     عب
    -0.06
    ivers
    -0.06
    Mask
    -0.06
    POSITIVE LOGITS
     사망
    0.06
     syslog
    0.06
    !↵↵↵
    0.06
     громадян
    0.06
     mutil
    0.06
    	user
    0.06
    战斗
    0.06
    	delay
    0.06
    名無しさん
    0.06
    _GenericClass
    0.06
    Act Density 0.024%

    No Known Activations