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

    Neuronpedia

    INDEX
    Explanations

    concepts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jail
    0.49
     HashSet
    0.47
    ning
    0.47
     গ্রহণ
    0.47
     เห็น
    0.47
     Goll
    0.46
     Price
    0.45
     Fashion
    0.45
     Dhoni
    0.45
     Atom
    0.45
    POSITIVE LOGITS
    ین
    0.59
    زب
    0.48
     imaginative
    0.46
    ارد
    0.46
    િક
    0.45
    дер
    0.45
    جاد
    0.44
     radiative
    0.43
    ون
    0.43
    לק
    0.43
    Act Density 0.010%

    No Known Activations