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

    Neuronpedia

    INDEX
    Explanations

    welcome to you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    names
    0.38
    Reverse
    0.38
    reverse
    0.38
     повер
    0.38
    ization
    0.37
     описа
    0.37
    SOL
    0.36
     doh
    0.36
     ختم
    0.35
     ^=
    0.35
    POSITIVE LOGITS
     aboard
    1.27
    aboard
    0.93
     onboard
    0.77
     welcome
    0.71
    欢迎
    0.66
     bienvenue
    0.65
    Welcome
    0.64
     Welcome
    0.64
     officially
    0.63
    来到
    0.62
    Act Density 0.004%

    No Known Activations