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

    Neuronpedia

    INDEX
    Explanations

    different forms of "information" and its associated phrases

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

    du followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brigens
    -0.42
    katapos
    -0.40
    agaimana
    -0.37
     Савезне
    -0.37
    bbene
    -0.36
     purpoſe
    -0.35
     neceff
    -0.34
    +#+
    -0.34
    acakt
    -0.33
     estação
    -0.32
    POSITIVE LOGITS
    JvmStatic
    0.55
     SafeMath
    0.51
     FetchType
    0.49
    些
    0.48
    nestjs
    0.48
    Tikang
    0.48
    enough
    0.48
    tät
    0.47
    verifyException
    0.47
    ContentAsync
    0.46
    Act Density 0.008%

    No Known Activations