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

    Neuronpedia

    INDEX
    Explanations

    punctuations and specific grammatical structures in sentences

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

    actions and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.34
     stanovnika
    -0.34
     nahilalakip
    -0.32
     juos
    -0.31
     kennis
    -0.28
    basicConfig
    -0.28
    IVEREF
    -0.28
    issenschaft
    -0.28
     preventiva
    -0.27
     kvalitet
    -0.27
    POSITIVE LOGITS
     препратки
    0.71
     فريبيس
    0.63
    ſſung
    0.59
    0.59
    <unused16>
    0.59
    <unused47>
    0.58
    клопе
    0.58
    <unused42>
    0.58
    <unused3>
    0.58
    <unused23>
    0.58
    Act Density 0.051%

    No Known Activations