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

    Neuronpedia

    INDEX
    Explanations

    specialized functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slides
    1.61
     ofta
    1.61
    삽
    1.60
     vaak
    1.58
    plementation
    1.55
     næ
    1.54
    iato
    1.51
    ressions
    1.50
    ء
    1.48
    ieel
    1.46
    POSITIVE LOGITS
    ⿳
    2.17
    8
    2.15
    apatillas
    2.12
    4
    2.07
    ⿹
    2.07
    物質
    2.06
    6
    2.04
    born
    2.02
    7
    2.01
    3
    2.00
    Act Density 0.059%

    No Known Activations