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

    Neuronpedia

    INDEX
    Explanations

    conversational elements that express uncertainty or hypothetical scenarios

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

    adverbs of degree and certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лтамалар
    -0.40
    eqn
    -0.38
     saat
    -0.38
    RTGC
    -0.36
     للاسماء
    -0.36
     certified
    -0.35
     and
    -0.35
    TM
    -0.35
    certified
    -0.34
    almaz
    -0.34
    POSITIVE LOGITS
     zijne
    0.59
    genodigd
    0.55
     sauvage
    0.53
     prêtres
    0.52
     juges
    0.52
     mijne
    0.52
     grecque
    0.51
     myſelf
    0.51
     plufieurs
    0.50
     Infór
    0.49
    Act Density 0.863%

    No Known Activations