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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =view
    -0.07
     فريق
    -0.07
    ndern
    -0.07
    pas
    -0.07
    ntity
    -0.07
     外部リンク
    -0.06
    urpose
    -0.06
    스트
    -0.06
    รค
    -0.06
    OSH
    -0.06
    POSITIVE LOGITS
    ereotype
    0.06
    搬
    0.06
     err
    0.06
    	my
    0.06
    บน
    0.06
     teachers
    0.06
     vaccine
    0.06
     incentives
    0.06
     Early
    0.05
     정말
    0.05
    Act Density 0.000%

    No Known Activations