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

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    truck
    -0.07
     kullanıcı
    -0.07
    NavigatorMove
    -0.07
     cpu
    -0.06
     getList
    -0.06
    iferay
    -0.06
     routes
    -0.06
    UARIO
    -0.06
    Conference
    -0.06
    Browsable
    -0.06
    POSITIVE LOGITS
     Vs
    0.07
    .amazon
    0.06
     sciences
    0.06
     사망
    0.06
     genital
    0.06
     Abdel
    0.06
     своими
    0.06
    atts
    0.06
    adel
    0.06
    ads
    0.06
    Act Density 0.011%

    No Known Activations