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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to symmetry and transformations in a formal context

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

    symmetry, identical, treated similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.65
    TagMode
    -0.64
    <unused74>
    -0.60
    <unused23>
    -0.60
    <unused43>
    -0.60
    <unused16>
    -0.59
    <unused28>
    -0.59
    <unused8>
    -0.59
    [@BOS@]
    -0.59
    <unused3>
    -0.59
    POSITIVE LOGITS
    symmetric
    0.34
     pattern
    0.34
     patterns
    0.33
     symmetric
    0.33
     symmetrical
    0.33
     cho
    0.32
     Symmetric
    0.31
    ệt
    0.31
    Ergebnisse
    0.30
    IsPostBack
    0.30
    Act Density 0.221%

    No Known Activations