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

    Neuronpedia

    INDEX
    Explanations

    Times New Roman and Higher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chante
    0.47
    啷
    0.43
    DropdownBox
    0.38
     idP
    0.38
    ববার
    0.37
    HideFlags
    0.37
     クリスマス
    0.37
    cmml
    0.37
     indeterm
    0.37
    <0xA5>
    0.37
    POSITIVE LOGITS
     Times
    0.56
     TIMES
    0.50
     times
    0.45
    QUARE
    0.43
    Times
    0.39
     romana
    0.39
     controlling
    0.38
     Zeiten
    0.38
     square
    0.37
     টাইমস
    0.37
    Act Density 0.001%

    No Known Activations