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

    Neuronpedia

    INDEX
    Explanations

    references to valuable or exceptional items

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

    gems, jewels, treasures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alter
    -0.37
    eteria
    -0.33
    blico
    -0.33
     Hivatalos
    -0.32
    multicolumn
    -0.31
     violenta
    -0.30
     plonge
    -0.30
     provisoire
    -0.30
     allgemeine
    -0.30
    ALTER
    -0.29
    POSITIVE LOGITS
     gems
    0.88
     treasures
    0.82
    RegressionTest
    0.82
     jewel
    0.82
    jewel
    0.81
     autorytatywna
    0.80
     treasure
    0.79
    treasure
    0.79
     jewels
    0.77
     gem
    0.76
    Act Density 0.013%

    No Known Activations