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

    Neuronpedia

    INDEX
    Explanations

    equality or equivalence in contexts

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

    video links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tarko
    -0.38
     landet
    -0.36
     steder
    -0.35
     jorden
    -0.35
    iteter
    -0.33
    릭터
    -0.30
    kjø
    -0.29
     fuertes
    -0.29
     cierre
    -0.29
     EnglishChoose
    -0.29
    POSITIVE LOGITS
    VersionUID
    0.73
    ScopeManager
    0.72
    OGND
    0.65
    CppMethod
    0.63
     kasarigan
    0.62
     video
    0.61
    principalTable
    0.60
    видео
    0.59
     vide
    0.58
    video
    0.57
    Act Density 0.001%

    No Known Activations