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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and the words enclosed within them

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    murder of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.96
    OGND
    -0.88
     nahilalakip
    -0.83
     AssemblyVersion
    -0.80
    StructEnd
    -0.77
    Демографія
    -0.73
    (!__
    -0.72
    EndProject
    -0.71
     <=",
    -0.69
     transfieras
    -0.65
    POSITIVE LOGITS
    ,‎
    0.58
    󠁴
    0.54
    Dabei
    0.54
     mAdapter
    0.52
    purl
    0.49
    υχ
    0.49
    uscular
    0.49
    glass
    0.48
     Muc
    0.48
     
    0.47
    Act Density 0.055%

    No Known Activations