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

    Neuronpedia

    INDEX
    Explanations

    code printing and returning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Plain
    0.45
    Genesis
    0.44
    0.43
    Ві
    0.43
    Bern
    0.42
     зре
    0.42
    Legacy
    0.42
    ◑
    0.42
    ICK
    0.41
    Beyond
    0.41
    POSITIVE LOGITS
     variabel
    0.51
    变量
    0.49
     seperate
    0.49
    onclick
    0.48
     everytime
    0.47
     variables
    0.46
     variable
    0.45
     =(
    0.45
     apabila
    0.44
     seper
    0.44
    Act Density 0.130%

    No Known Activations