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

    Neuronpedia

    INDEX
    Explanations

    abstract philosophical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ซึ่ง
    0.41
     különböz
    0.40
    instead
    0.39
    which
    0.37
     ossia
    0.36
     altid
    0.35
     altijd
    0.34
    utas
    0.34
     sawa
    0.33
     allemaal
    0.33
    POSITIVE LOGITS
     insofar
    1.14
     except
    0.81
     unless
    0.79
     according
    0.75
     zumindest
    0.74
     menurut
    0.73
     within
    0.72
     inasmuch
    0.72
    unless
    0.70
     بالنسبه
    0.70
    Act Density 0.156%

    No Known Activations