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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements and symbols

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

    symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.63
     ſeines
    -0.60
     ſeyn
    -0.59
    ſſung
    -0.59
     Menſchen
    -0.59
     パンチラ
    -0.59
    niſſe
    -0.58
    ittoria
    -0.58
    <unused20>
    -0.58
    <unused14>
    -0.58
    POSITIVE LOGITS
    期刊论文
    0.49
     nakalista
    0.41
    HttpDelete
    0.38
     nueces
    0.34
    cemment
    0.34
    BeginInit
    0.34
     itemView
    0.33
    beiros
    0.33
    ientôt
    0.33
     posteriormente
    0.33
    Act Density 0.110%

    No Known Activations