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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and detailed discussions about specific subjects

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

    collections of photographs and documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.53
     שוליים
    -0.40
     Predictive
    -0.36
     Steal
    -0.35
     Taktlose
    -0.35
     steal
    -0.34
    Билгалдахарш
    -0.33
     AppCompatTheme
    -0.32
    Pyx
    -0.32
     Failure
    -0.31
    POSITIVE LOGITS
    лтемелер
    0.57
     ſtate
    0.55
     poffe
    0.50
    Personendaten
    0.49
     ſta
    0.49
    wiſe
    0.48
     Colección
    0.47
    ViewFeatures
    0.47
     coleção
    0.45
     témo
    0.45
    Act Density 0.037%

    No Known Activations