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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Remember
    0.44
     Ru
    0.41
    वाणी
    0.41
     Remember
    0.40
     सबकुछ
    0.39
    Luck
    0.39
    are
    0.38
     سنج
    0.38
     සඳ
    0.37
     fox
    0.37
    POSITIVE LOGITS
    ⵓ
    0.47
     пье
    0.43
    不會
    0.41
    ፔ
    0.40
     craziness
    0.40
     полномо
    0.39
    不会
    0.38
    ዑ
    0.38
    0.37
    䚯
    0.37
    Act Density 0.000%

    No Known Activations