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

    Neuronpedia

    INDEX
    Explanations

    romantic interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    做什么
    0.84
    ০
    0.77
    woven
    0.76
    nú
    0.74
    แค่
    0.74
    rophages
    0.73
    Pepper
    0.72
    do
    0.72
    princip
    0.72
    aller
    0.71
    POSITIVE LOGITS
    ли
    0.71
     Lithuan
    0.71
     DMA
    0.71
     rumour
    0.71
    ле
    0.68
     Möglichkeit
    0.66
    恼
    0.64
     dismin
    0.63
     glaring
    0.63
     hervorrag
    0.63
    Act Density 0.001%

    No Known Activations