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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "because" in various contexts

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

    just because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thâu
    -0.50
    ViewInit
    -0.48
    Jereo
    -0.41
     vuestros
    -0.41
    énario
    -0.40
     onView
    -0.40
     الرياضيه
    -0.40
    MigrationBuilder
    -0.39
    Билгалдахарш
    -0.38
    cakup
    -0.37
    POSITIVE LOGITS
    Fancy
    0.53
     '{@
    0.50
     Arbitrary
    0.49
    randn
    0.48
     Fancy
    0.47
    ValueStyle
    0.46
     autorytatywna
    0.46
    putBoolean
    0.45
    rand
    0.44
     totalSupply
    0.44
    Act Density 0.006%

    No Known Activations