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

    Neuronpedia

    INDEX
    Explanations

    Lists and item selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Discussions
    -0.07
     congrat
    -0.07
    교육
    -0.07
    가는
    -0.06
    REAK
    -0.06
    Rot
    -0.06
    ska
    -0.06
    roleum
    -0.06
     ایران
    -0.06
    wią
    -0.06
    POSITIVE LOGITS
    Amy
    0.08
     Jenny
    0.07
     Tec
    0.06
    (element
    0.06
                        ↵
    0.06
    енности
    0.06
    apphire
    0.06
     resurrect
    0.06
    003
    0.06
     Prism
    0.06
    Act Density 0.002%

    No Known Activations