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

    Neuronpedia

    INDEX
    Explanations

    sections of text that include emphasis markers, like bold formatting

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

    author, abstract, introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.46
     виправивши
    -0.42
    TagMode
    -0.38
    EDEFAULT
    -0.37
    lijken
    -0.37
    Tre
    -0.36
     Tapes
    -0.35
    marle
    -0.35
     Kipling
    -0.35
    MediaStore
    -0.35
    POSITIVE LOGITS
     ſch
    0.50
    Autoritní
    0.49
     myſelf
    0.49
     eſſ
    0.47
     ſta
    0.47
     ſind
    0.46
    ))^
    0.44
    󠁴
    0.43
     ſtill
    0.43
     themſelves
    0.43
    Act Density 0.009%

    No Known Activations