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

    Neuronpedia

    INDEX
    Explanations

    complex math equations or proofs

    oai_token-act-pair · gemini-2.0-flash

    say "Q"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Qu
    -1.65
    Qu
    -1.55
     QU
    -1.54
     Quar
    -1.52
     qu
    -1.52
    Quar
    -1.49
     Quin
    -1.46
     CQ
    -1.41
     Que
    -1.41
     q
    -1.41
    POSITIVE LOGITS
     Bergh
    0.65
     Spann
    0.52
     Berman
    0.52
     Spicer
    0.50
    untergang
    0.48
     désolés
    0.47
    rhosis
    0.47
    ดอก
    0.46
    BorderFactory
    0.46
    Cyfeiriadau
    0.45
    Act Density 1.245%

    No Known Activations