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

    Neuronpedia

    INDEX
    Explanations

    numbers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🈷
    0.83
     overtime
    0.82
    🧞
    0.82
    👘
    0.81
    🔡
    0.80
    🕴
    0.79
     prevalent
    0.76
     perplex
    0.76
    🗯
    0.76
    📤
    0.75
    POSITIVE LOGITS
    3
    0.77
    nde
    0.72
    6
    0.71
    4
    0.71
    ige
    0.71
    ript
    0.71
    <unused1744>
    0.70
    2
    0.69
    1
    0.69
    erti
    0.68
    Act Density 0.565%

    No Known Activations