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

    Neuronpedia

    INDEX
    Explanations

    "Re" prefix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Re
    4.02
    Re
    3.84
     Be
    3.36
    Be
    3.08
     Se
    2.52
     re
    2.43
     Ge
    2.32
    Se
    2.29
     Te
    2.28
     Me
    2.18
    POSITIVE LOGITS
    з
    0.66
    ц
    0.65
    Curr
    0.63
    anoi
    0.62
    एस
    0.62
    壹
    0.62
    ToDelete
    0.61
    爆炸
    0.61
     ഉട
    0.61
    rods
    0.61
    Act Density 0.058%

    No Known Activations