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

    Neuronpedia

    INDEX
    Explanations

    woodchuck chuck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sh
    0.44
    Summit
    0.43
     Tsu
    0.42
    VERTISING
    0.40
    Всім
    0.40
    Arch
    0.40
    Security
    0.40
    Ai
    0.39
    Week
    0.39
    elitian
    0.39
    POSITIVE LOGITS
    手
    0.51
    лизи
    0.50
     социа
    0.49
     brazo
    0.47
    毆
    0.47
     реконструк
    0.47
    ра
    0.46
     armado
    0.46
     рей
    0.46
     уни
    0.45
    Act Density 0.005%

    No Known Activations