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

    Neuronpedia

    INDEX
    Explanations

    references to online articles or essays

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

    Pa, Cir, Kan citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    écart
    -0.35
    ampung
    -0.31
    apparence
    -0.31
    atmosphère
    -0.31
     ruinas
    -0.31
    pri
    -0.30
    aménagement
    -0.30
    accompagnement
    -0.29
     Wahrheit
    -0.29
    époque
    -0.29
    POSITIVE LOGITS
     tartalomajánló
    0.82
     Италијани
    0.74
     Савезне
    0.73
    uxxxx
    0.71
    Personendaten
    0.70
    InjectAttribute
    0.70
     ſind
    0.68
     ſein
    0.67
    iſen
    0.66
     kaarangay
    0.64
    Act Density 0.004%

    No Known Activations