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

    Neuronpedia

    INDEX
    Explanations

    Number sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exp
    -0.07
    抜け
    -0.07
    ést
    -0.07
    _HELPER
    -0.07
     goggles
    -0.07
     Sexual
    -0.07
    לוק
    -0.07
     modne
    -0.06
     ::::::::
    -0.06
    lessly
    -0.06
    POSITIVE LOGITS
     amend
    0.07
    flatMap
    0.07
     tell
    0.07
    采访
    0.07
     sums
    0.06
     Glacier
    0.06
    VIP
    0.06
    我不想
    0.06
    จ
    0.06
     epochs
    0.06
    Act Density 0.005%

    No Known Activations