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

    Neuronpedia

    INDEX
    Explanations

    references to governmental actions and legal proceedings related to national security

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

    Text after a comma

    np_acts-logits-general · gemini-2.0-flash

    Well, out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wtf
    -0.68
     WTF
    -0.60
    OuterClass
    -0.59
    []{"
    -0.56
     zamiast
    -0.56
    WTF
    -0.54
    FUCK
    -0.52
    </h3>
    -0.52
    !“
    -0.51
    baye
    -0.51
    POSITIVE LOGITS
     Савезне
    0.86
     كومونز
    0.76
     CreateTagHelper
    0.71
    migrationBuilder
    0.67
     effectivement
    0.65
    Certainly
    0.64
     nakalista
    0.63
    OGND
    0.62
     समीक्षाओं
    0.62
     Certainly
    0.61
    Act Density 0.098%

    No Known Activations