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

    Neuronpedia

    INDEX
    Explanations

    references to individuals speaking or providing statements

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

    Attribution, followed by "said" or "says"

    np_acts-logits-general · gemini-2.0-flash

    reporting verbs after subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onAttach
    -0.61
     surely
    -0.54
    nEnter
    -0.51
    joyed
    -0.51
    XtraGrid
    -0.50
    joy
    -0.49
    asserole
    -0.48
     certainly
    -0.48
    pter
    -0.47
     smart
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    WriteBarrier
    0.68
     متعلقه
    0.63
    KommentareTeilen
    0.63
    RSpec
    0.59
    MessageTagHelper
    0.59
    uxxxx
    0.59
     ujednoznacz
    0.58
    enumii
    0.58
    VersionUID
    0.58
    Act Density 0.142%

    No Known Activations