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

    Neuronpedia

    INDEX
    Explanations

    encompass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transmitter
    -0.07
    λίου
    -0.07
     proxies
    -0.07
    ‐'
    -0.06
     compliance
    -0.06
     گفته
    -0.06
     despair
    -0.06
    徐
    -0.06
     appears
    -0.06
     prostitut
    -0.06
    POSITIVE LOGITS
    .conv
    0.07
    Unit
    0.06
    -ranking
    0.06
    Ê
    0.06
    _pm
    0.06
     EVEN
    0.06
     servisi
    0.06
    ,std
    0.06
    /.↵
    0.06
    _linked
    0.06
    Act Density 0.444%

    No Known Activations