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

    Neuronpedia

    INDEX
    Explanations

    from and its equivalents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irk
    0.39
    icer
    0.38
    uchtigkeit
    0.38
    aber
    0.38
    ertz
    0.36
    platin
    0.35
    hael
    0.35
    boyfriend
    0.35
    சாமி
    0.34
    opera
    0.34
    POSITIVE LOGITS
     từ
    0.46
    จาก
    0.46
     from
    0.46
     kutoka
    0.45
     från
    0.45
     від
    0.41
    ー
    0.40
    پ
    0.39
     dari
    0.39
     perspici
    0.39
    Act Density 0.000%

    No Known Activations