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

    Neuronpedia

    INDEX
    Explanations

    specific terminology related to neural networks and their architecture

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

    neural network nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    charpe
    -0.42
     Planeta
    -0.40
     patchy
    -0.37
     guaranteeing
    -0.36
     bas
    -0.36
     ठ
    -0.35
     Planet
    -0.34
    텝
    -0.33
    ఖ
    -0.33
     crowns
    -0.33
    POSITIVE LOGITS
    SharedCtor
    0.64
     nahilalakip
    0.56
    oredCriteria
    0.54
    Personensuche
    0.54
    ፩
    0.52
     disambiguazione
    0.49
    UnusedPrivate
    0.48
    참고
    0.47
    PreInfinity
    0.47
     Exactos
    0.47
    Act Density 0.020%

    No Known Activations