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

    Neuronpedia

    INDEX
    Explanations

    references to "elements" in various contexts

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

    "element"

    np_acts-logits-general · gemini-2.0-flash

    element

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
    hoeddwyd
    -0.57
    InjectMocks
    -0.57
    HasForeignKey
    -0.56
     estekak
    -0.55
     linkovi
    -0.54
     Efq
    -0.53
    tonsoft
    -0.52
     محفوظة
    -0.50
     Audiodateien
    -0.49
    POSITIVE LOGITS
     Element
    0.65
    Element
    0.63
     ELEMENT
    0.62
     element
    0.60
    Ele
    0.56
    ele
    0.55
     ELE
    0.55
     Ele
    0.54
     elemen
    0.54
    ELEMENT
    0.53
    Act Density 0.142%

    No Known Activations