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

    Neuronpedia

    INDEX
    Explanations

    ct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chỉ
    -0.07
    економ
    -0.06
    �
    -0.06
    private
    -0.06
     Demon
    -0.06
     criticism
    -0.06
     Ř
    -0.06
    _multip
    -0.06
     YEARS
    -0.06
     yaşam
    -0.06
    POSITIVE LOGITS
     towering
    0.06
    ΟΥ
    0.06
    	hr
    0.06
     tract
    0.06
    !!}↵
    0.06
    nts
    0.06
     firewall
    0.06
    403
    0.06
     kao
    0.06
     hk
    0.06
    Act Density 0.002%

    No Known Activations