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

    Neuronpedia

    INDEX
    Explanations

    technical terms and mathematical concepts related to gauge theory and transformations

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

    which results in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.45
     étoient
    -0.45
     houſe
    -0.44
     pleaſure
    -0.42
    ​​​​
    -0.42
     étoit
    -0.42
     owne
    -0.41
     ️
    -0.41
     XNUMX
    -0.41
    ️
    -0.40
    POSITIVE LOGITS
     quantum
    0.58
     perturb
    0.55
     renon
    0.55
     manifestly
    0.55
     qualitatively
    0.53
     inderdaad
    0.52
     gouvern
    0.52
     regime
    0.51
     banyo
    0.51
     PHYSICAL
    0.51
    Act Density 3.285%

    No Known Activations