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

    Neuronpedia

    INDEX
    Explanations

    nestled followed by location prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    änen
    0.59
    kc
    0.58
     Polytechn
    0.55
     categor
    0.54
    0.53
    渍
    0.53
    ocus
    0.52
    xls
    0.52
    nt
    0.52
    ige
    0.52
    POSITIVE LOGITS
    ت
    0.96
    ’).
    0.84
    رک
    0.83
    기
    0.78
    み
    0.75
    는다
    0.75
    مک
    0.74
    ه
    0.73
     ک
    0.72
    f
    0.71
    Act Density 0.001%

    No Known Activations