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

    Neuronpedia

    INDEX
    Explanations

    names of authors or contributors in written pieces

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

    Tokens after people's names

    np_acts-logits-general · gemini-2.0-flash

    author bylines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.98
    BeginContext
    -0.96
    DockStyle
    -0.89
    WriteBarrier
    -0.89
    InjectAttribute
    -0.85
     resourceCulture
    -0.84
    XmlAccessType
    -0.83
    kloped
    -0.81
    ContentAlignment
    -0.79
    NgModule
    -0.79
    POSITIVE LOGITS
    ↵↵
    0.54
     teren
    0.48
     writing
    0.48
    (@
    0.47
    with
    0.47
    ↵↵↵↵
    0.46
     &
    0.45
    ↵↵↵
    0.44
     Ph
    0.43
     with
    0.43
    Act Density 0.186%

    No Known Activations