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

    Neuronpedia

    INDEX
    Explanations

    change course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    杞
    0.45
    一件
    0.43
     udziel
    0.40
     admissibility
    0.40
     अराज
    0.40
     അംഗ
    0.39
    凍
    0.39
     تلك
    0.39
     বিপক্ষে
    0.39
     prolific
    0.38
    POSITIVE LOGITS
     //
    0.54
     //{
    0.41
     $(
    0.40
     ===
    0.39
    ^{(
    0.39
     &&
    0.38
    clusively
    0.38
     ;
    0.38
    icamente
    0.37
     //[
    0.37
    Act Density 0.000%

    No Known Activations