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

    Neuronpedia

    INDEX
    Explanations

    welcome to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     привет
    0.56
     શુભેચ્છ
    0.53
     приветствую
    0.53
     શુભેચ્છાઓ
    0.52
     помощи
    0.51
     welcomes
    0.50
     welcoming
    0.49
     сообщает
    0.48
     goodbye
    0.48
     привіт
    0.47
    POSITIVE LOGITS
     into
    0.55
    到
    0.52
     on
    0.48
     dient
    0.46
    諫
    0.45
     parar
    0.44
     pared
    0.44
     to
    0.44
    ρια
    0.44
     alone
    0.43
    Act Density 0.003%

    No Known Activations