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

    Neuronpedia

    INDEX
    Explanations

    sentences that express opinions or evaluations of ideas or creative works

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

    after nouns

    np_acts-logits-general · gemini-2.0-flash

    concepts and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁢
    -0.69
     تضيفلها
    -0.67
    ATTN
    -0.59
    endpush
    -0.59
    ThroughAttribute
    -0.57
     selaku
    -0.56
    érité
    -0.55
     onOptions
    -0.55
     NoSuch
    -0.54
    gnon
    -0.52
    POSITIVE LOGITS
     indeed
    0.88
    indeed
    0.72
     overall
    0.67
     nonetheless
    0.64
    Indeed
    0.62
     Overall
    0.59
    considering
    0.59
     Indeed
    0.59
     deserving
    0.58
     deserves
    0.58
    Act Density 0.240%

    No Known Activations