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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

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

    Code that prints to the console

    np_acts-logits-general · gemini-2.0-flash

    printing to console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.06
    Jeografia
    -0.77
    SourceChecksum
    -0.76
    UnsafeEnabled
    -0.75
    Personendaten
    -0.75
    ]--;
    -0.73
     ComVisible
    -0.73
     resourceCulture
    -0.72
     fubject
    -0.71
    estacks
    -0.69
    POSITIVE LOGITS
    println
    0.88
     println
    0.59
     fau
    0.48
    ainville
    0.47
    prit
    0.46
    WGS
    0.46
     Bom
    0.45
    imental
    0.44
     Bia
    0.44
    SAI
    0.44
    Act Density 0.010%

    No Known Activations