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

    Neuronpedia

    INDEX
    Explanations

    concepts related to affirmative action and its implications

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

    Prepositions and possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    technical and common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.10
    OGND
    -1.06
    rungsseite
    -1.00
    ]--;
    -0.99
     kaarangay
    -0.98
    ंदीखरीदारी
    -0.92
     "..\..\..\
    -0.91
     &___
    -0.91
    AndEndTag
    -0.91
     nahilalakip
    -0.91
    POSITIVE LOGITS
    <eos>
    0.53
      
    0.50
     solchen
    0.49
    小小的
    0.42
    .
    0.41
    </strong>
    0.41
     negras
    0.40
     solche
    0.40
     diza
    0.39
     such
    0.39
    Act Density 1.458%

    No Known Activations