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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or possibilities

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

    objective matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comprometido
    -0.71
     Paglinawan
    -0.61
    protoimpl
    -0.55
    bewerken
    -0.54
    OGND
    -0.53
     Masyarakat
    -0.52
     Lingkungan
    -0.51
    Viited
    -0.49
    strnc
    -0.49
     ComVisible
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.50
     objective
    0.41
     Objective
    0.38
    MessageOf
    0.38
    objective
    0.37
     objectives
    0.35
    MemoryWarning
    0.34
     matters
    0.32
     подо
    0.32
     Rha
    0.30
    Act Density 0.053%

    No Known Activations