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

    Neuronpedia

    INDEX
    Explanations

    little, a little bit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     및
    0.57
     אך
    0.55
     पश्चात
    0.54
    および
    0.52
     மற்றும்
    0.47
    של
    0.46
     पुढील
    0.46
     अथवा
    0.45
     נוס
    0.45
     ומ
    0.45
    POSITIVE LOGITS
     ahorita
    0.65
     people
    0.63
    這樣子
    0.60
     acá
    0.58
     poquito
    0.55
     cosas
    0.52
     tady
    0.51
     tutaj
    0.50
    なんか
    0.50
     bisschen
    0.49
    Act Density 0.021%

    No Known Activations