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

    Neuronpedia

    INDEX
    Explanations

    words indicating a continuation or summation of information

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

    so far / thus far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.49
    Rüyada
    -0.47
    encodeWith
    -0.42
    complexContent
    -0.41
     CanadaChoose
    -0.40
    Personendaten
    -0.40
    awaiter
    -0.39
    modelBuilder
    -0.38
     Schatz
    -0.37
    ölkerung
    -0.37
    POSITIVE LOGITS
     '\\;'
    0.55
    iotensin
    0.46
    istoitu
    0.45
     gettyimages
    0.44
     Advantage
    0.44
     getCurrent
    0.43
     current
    0.43
    amentlich
    0.42
     iſt
    0.42
    othesis
    0.42
    Act Density 0.072%

    No Known Activations