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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal or procedural language

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

    phrases based on preceding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.50
     ErrIntOverflow
    -0.38
    раздо
    -0.36
     aanwezig
    -0.36
     därför
    -0.36
    után
    -0.35
    zzleHttp
    -0.35
    liferay
    -0.35
    zuführen
    -0.35
     temperatuur
    -0.35
    POSITIVE LOGITS
     plateado
    0.50
     recientemente
    0.45
     gynhyrchwyd
    0.43
    nyttet
    0.43
     previously
    0.41
     consulted
    0.40
     Weisheit
    0.40
     soeur
    0.40
    octanol
    0.40
    sold
    0.40
    Act Density 0.516%

    No Known Activations