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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and relationships, particularly in algebra and geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical concepts or objects after "of"

    np_acts-logits-general · gemini-2.0-flash

    alternating tensors and vectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -0.93
     lèvres
    -0.82
     genoux
    -0.81
     âmes
    -0.76
     rayures
    -0.73
     témoins
    -0.70
     larmes
    -0.69
     jambes
    -0.68
    ⓧ
    -0.65
     écrits
    -0.64
    POSITIVE LOGITS
     functions
    0.94
     quantities
    0.90
     expressions
    0.86
     sets
    0.81
     pairs
    0.81
     objects
    0.81
     lists
    0.80
     vectors
    0.77
     matrices
    0.77
     relations
    0.75
    Act Density 1.689%

    No Known Activations