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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     industri
    0.51
     acet
    0.49
     tus
    0.49
    你
    0.46
    ுகள்
    0.46
     mismo
    0.45
     gin
    0.45
     صنایع
    0.45
     concentrations
    0.45
     amyg
    0.44
    POSITIVE LOGITS
    라는
    0.44
     కీలక
    0.43
    ли
    0.41
    יי
    0.41
     関数
    0.40
    RI
    0.40
    לי
    0.40
     لکھ
    0.40
    匼
    0.39
    一生
    0.39
    Act Density 0.006%

    No Known Activations