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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of duality or opposing perspectives

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

    side of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     number
    -0.36
     número
    -0.35
    Билгалдахарш
    -0.34
    Numerade
    -0.33
     årene
    -0.31
     developers
    -0.31
     LoginComponent
    -0.30
     medulla
    -0.29
    Creators
    -0.29
     Number
    -0.29
    POSITIVE LOGITS
    ReusableCell
    0.63
    Vanjske
    0.60
    Хьажоргаш
    0.60
    DockStyle
    0.60
     Opposite
    0.59
    sides
    0.58
    crossing
    0.57
    ⤹
    0.56
    KommentareTeilen
    0.56
    Crossing
    0.54
    Act Density 0.010%

    No Known Activations