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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate research findings or conclusions

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

    demonstrate findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     législation
    -0.44
    zise
    -0.41
     Kand
    -0.40
     photographe
    -0.39
     preocupação
    -0.38
     Jacobsen
    -0.38
     уж
    -0.37
     Baumann
    -0.36
    roppo
    -0.36
     Kementerian
    -0.36
    POSITIVE LOGITS
    EndInit
    0.60
     חיצוניים
    0.56
     nakalista
    0.52
    StructEnd
    0.52
     EconPapers
    0.51
    AnimationsModule
    0.51
    addContainerGap
    0.49
    出版年
    0.47
     protoimpl
    0.47
    verwijspagina
    0.47
    Act Density 0.841%

    No Known Activations