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

    Neuronpedia

    INDEX
    Explanations

    code parameter settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    活力
    0.37
     খেয়ে
    0.35
    <unused717>
    0.35
    ังสือ
    0.34
     Haemat
    0.34
    াহরণ
    0.33
    <unused742>
    0.33
    ંત્રણ
    0.32
    Terry
    0.32
    രുവന
    0.32
    POSITIVE LOGITS
    =
    0.84
    ="
    0.62
     =
    0.49
    =${
    0.48
    =\
    0.48
    =$
    0.47
    =[
    0.46
    =(
    0.45
    ='
    0.44
    ={
    0.44
    Act Density 0.078%

    No Known Activations