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

    Neuronpedia

    INDEX
    Explanations

    references to the object or instance being acted upon

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

    this->_

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HideFlags
    -0.57
     CanadaChoose
    -0.52
     Comprometido
    -0.45
    Autoritní
    -0.45
    expandindo
    -0.41
     Photocase
    -0.41
    seamnă
    -0.41
    省市镇
    -0.40
    Datuak
    -0.40
    tanleria
    -0.39
    POSITIVE LOGITS
    MethodManager
    0.49
     this
    0.49
    classnames
    0.47
    revalidate
    0.47
     standard
    0.45
     always
    0.44
     close
    0.44
    MutableLiveData
    0.43
    \{\\
    0.43
     feeling
    0.43
    Act Density 0.003%

    No Known Activations