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

    Neuronpedia

    INDEX
    Explanations

    welcome greeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]{
    0.87
    ]}{
    0.87
    ]{\
    0.85
    )}{
    0.78
    )}-\
    0.78
    /}{
    0.77
    }}{
    0.75
    }]{
    0.75
    ebab
    0.75
    iquer
    0.75
    POSITIVE LOGITS
    Welcome
    0.78
    welcome
    0.78
     Meg
    0.77
     welcome
    0.76
     Welcome
    0.72
    MASK
    0.71
    Meg
    0.71
     डेमो
    0.69
     сможете
    0.69
     Mega
    0.68
    Act Density 0.001%

    No Known Activations