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

    Neuronpedia

    INDEX
    Explanations

    command not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bagi
    1.25
    덟
    1.16
     решили
    1.15
     Fonts
    1.13
     вирі
    1.11
     ہیں
    1.10
    рование
    1.09
     лікар
    1.09
    平成
    1.07
    もり
    1.06
    POSITIVE LOGITS
    do
    1.30
     incentiv
    1.18
    don
    1.17
    incent
    1.17
     ultraf
    1.17
    most
    1.16
    ️
    1.16
     instructive
    1.14
    s
    1.13
    dor
    1.12
    Act Density 0.000%

    No Known Activations