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
     entend
    -0.08
     trainer
    -0.07
    	item
    -0.07
    교
    -0.07
    声明
    -0.07
    )#
    -0.06
     PSI
    -0.06
    /t
    -0.06
    !!.
    -0.06
    	event
    -0.06
    POSITIVE LOGITS
    ************************
    0.07
     Ney
    0.06
    ohl
    0.06
    iven
    0.06
    ARR
    0.06
     λο
    0.06
    ACCOUNT
    0.06
    칙
    0.06
    άρχ
    0.06
     ауд
    0.06
    Act Density 0.104%

    No Known Activations