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

    Neuronpedia

    INDEX
    Explanations

    themes related to teamwork and collaboration in a professional context

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

    Following pronouns and possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    categories and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.91
    ésultats
    -0.82
    MLLoader
    -0.81
    MessageOf
    -0.81
    BeginContext
    -0.81
     témoig
    -0.77
    ロウィン
    -0.76
     itſelf
    -0.75
    <unused52>
    -0.74
    AnimationsModule
    -0.74
    POSITIVE LOGITS
    ↵↵
    0.57
     |
    0.43
    ↵
    0.42
     The
    0.40
     
    0.40
     This
    0.39
    ↵↵↵
    0.38
     They
    0.37
     https
    0.36
     These
    0.36
    Act Density 0.517%

    No Known Activations