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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ####
    -0.06
    Ins
    -0.06
     рублей
    -0.06
    _Pro
    -0.06
     lbl
    -0.06
     Ling
    -0.06
    Highlight
    -0.06
     Watson
    -0.06
    undler
    -0.06
     pencils
    -0.06
    POSITIVE LOGITS
     nell
    0.07
    .coroutines
    0.07
    南省
    0.07
     ΠΑΝ
    0.07
    UserId
    0.07
    yles
    0.06
    ban
    0.06
    गर
    0.06
     sometime
    0.06
    ernes
    0.06
    Act Density 0.007%

    No Known Activations