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

    Neuronpedia

    INDEX
    Explanations

    not directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mensch
    0.45
    Humans
    0.43
    Govern
    0.42
     mennesker
    0.41
    ucker
    0.41
    Stack
    0.41
    Listener
    0.40
    生活中
    0.40
    isp
    0.40
     człowie
    0.40
    POSITIVE LOGITS
     ipak
    0.52
     plums
    0.49
     კარ
    0.46
     peony
    0.45
     linal
    0.44
     décoration
    0.44
     plum
    0.43
     আকর্ষণ
    0.43
     dividends
    0.43
     aliphatic
    0.43
    Act Density 0.012%

    No Known Activations