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

    Neuronpedia

    INDEX
    Explanations

    terms related to structured systems and classifications

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

    describing a state or condition

    np_acts-logits-general · gemini-2.0-flash

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -1.22
    Personendaten
    -1.10
    AndEndTag
    -1.10
     Roskov
    -1.06
    sizeCache
    -1.01
     feroit
    -1.01
     étoit
    -1.01
    SourceChecksum
    -1.00
     Италијани
    -1.00
    InjectAttribute
    -0.97
    POSITIVE LOGITS
     inter
    0.61
    …
    0.60
     E
    0.59
    -
    0.58
     …
    0.57
     versus
    0.57
     and
    0.57
     non
    0.56
     he
    0.55
    </em>
    0.55
    Act Density 0.565%

    No Known Activations