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

    Neuronpedia

    INDEX
    Explanations

    fill in the blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Azer
    0.37
     der
    0.35
     cover
    0.33
     bia
    0.32
     marcar
    0.32
     mis
    0.32
     Punkt
    0.32
     Solve
    0.32
     Activate
    0.32
     Aug
    0.31
    POSITIVE LOGITS
    ___________
    0.41
    ____________
    0.40
    ______________
    0.39
    _____________
    0.38
    으며
    0.37
    ____
    0.35
    _______
    0.35
    ($"{
    0.35
     ನೀಡ
    0.35
     ____________
    0.35
    Act Density 0.027%

    No Known Activations