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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crit
    -0.08
    tent
    -0.07
    closest
    -0.07
    ену
    -0.07
    generate
    -0.07
    empt
    -0.07
    AO
    -0.07
    раль
    -0.07
     Having
    -0.07
    娜
    -0.07
    POSITIVE LOGITS
     createUser
    0.07
    #
    0.07
    =j
    0.06
     χρή
    0.06
     filtr
    0.06
    และ
    0.06
    }")]↵
    0.06
    	xtype
    0.06
     há
    0.06
     ниже
    0.06
    Act Density 0.026%

    No Known Activations