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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" or its variants in different forms

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

    past existence and duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quela
    -0.41
     lendemain
    -0.36
    iosamente
    -0.35
    TopLevel
    -0.34
          
    -0.34
     instance
    -0.33
    ртқы
    -0.33
    <eos>
    -0.31
     morgens
    -0.31
     personnage
    -0.31
    POSITIVE LOGITS
    은
    0.90
    errHandler
    0.81
    え
    0.78
    rungsseite
    0.77
    える
    0.73
     은
    0.72
    initWith
    0.71
     doubtnut
    0.70
     protoimpl
    0.70
    えて
    0.70
    Act Density 0.003%

    No Known Activations