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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causal relationships or dependencies

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

    foreign language words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    God
    -0.42
    pó
    -0.41
     bubble
    -0.41
    Dutch
    -0.39
     bub
    -0.39
    Mono
    -0.39
    Iso
    -0.39
    French
    -0.39
    Ministry
    -0.38
     Iso
    -0.38
    POSITIVE LOGITS
     विश्वसनीयता
    0.68
     relâche
    0.56
    StoreMessageInfo
    0.55
     Normdatei
    0.54
    kijken
    0.53
     також
    0.53
     fatores
    0.52
     noemen
    0.52
     conseguenza
    0.51
     verschill
    0.51
    Act Density 0.111%

    No Known Activations