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

    Neuronpedia

    INDEX
    Explanations

    Great Expectations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Tr
    -0.07
    [length
    -0.06
     Dě
    -0.06
     ingin
    -0.06
    _COUNTRY
    -0.06
     Method
    -0.06
    \model
    -0.06
    -0.06
    .TRA
    -0.06
     Grain
    -0.06
    POSITIVE LOGITS
     humour
    0.06
    hw
    0.06
     victories
    0.06
     gaz
    0.06
     huge
    0.06
    htags
    0.06
     gazet
    0.06
    blind
    0.06
     سیستم
    0.06
     音
    0.06
    Act Density 0.011%

    No Known Activations