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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and proper nouns associated with notable names, inventions, or entities

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

    in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.44
    styleable
    -0.33
     []:
    -0.29
    ContentAsync
    -0.26
    InstrumentedTest
    -0.26
    EDEFAULT
    -0.23
     presidenta
    -0.22
     echa
    -0.22
    WriteLiteral
    -0.22
    {{--
    -0.22
    POSITIVE LOGITS
    ſelben
    0.89
     queſta
    0.82
    0.74
    ஦
    0.74
     queſto
    0.73
    <unused42>
    0.73
    <unused43>
    0.73
    <unused41>
    0.73
    [@BOS@]
    0.73
    <unused23>
    0.73
    Act Density 0.267%

    No Known Activations