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

    Neuronpedia

    INDEX
    Explanations

    words starting with pat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h3>
    -2.92
     \_
    -2.33
     —
    -2.30
     are
    -2.28
    挫
    -2.27
    or
    -2.27
    ."
    -2.25
    咈
    -2.16
    </strong>
    -2.16
    ↵↵
    -2.14
    POSITIVE LOGITS
    そういえば
    3.33
    '
    2.86
    </b>
    2.73
     美甲
    2.59
    {
    2.58
    洇
    2.56
    饪
    2.55
    genodigd
    2.52
     einschließlich
    2.48
    Responding
    2.39
    Act Density 0.041%

    No Known Activations