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

    Neuronpedia

    INDEX
    Explanations

    adding items to lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⲑ
    0.44
     êtres
    0.42
    isPreviewStarted
    0.39
    ￳
    0.38
     समर्थ
    0.38
    闗
    0.38
     حياة
    0.38
     मिळू
    0.38
     remise
    0.38
    وں
    0.37
    POSITIVE LOGITS
     append
    1.51
    append
    1.45
     appending
    1.32
     Append
    1.29
    Append
    1.26
     adding
    1.20
     +=
    1.17
     добавля
    1.17
    appendChild
    1.16
     add
    1.12
    Act Density 0.040%

    No Known Activations