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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভুট্ট
    0.40
     رجسٹر
    0.40
    Importer
    0.40
    检
    0.39
    ㎝
    0.39
    ocese
    0.39
    Evento
    0.39
    মাপ
    0.38
    劧
    0.38
    dostęp
    0.38
    POSITIVE LOGITS
    to
    0.44
     il
    0.41
     as
    0.39
     elektromagnet
    0.38
     j
    0.38
     Fahrenheit
    0.38
     Paul
    0.38
     elliptical
    0.37
     Asher
    0.37
     درجه
    0.36
    Act Density 0.001%

    No Known Activations