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

    Neuronpedia

    INDEX
    Explanations

    twin primes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    單位
    0.45
     jednost
    0.42
    生日
    0.40
    cyon
    0.40
    جل
    0.40
    jourd
    0.40
    混ぜ
    0.39
    ജി
    0.39
     calcular
    0.39
     biologiques
    0.39
    POSITIVE LOGITS
     Candidates
    0.50
     candidates
    0.48
     twin
    0.47
     twins
    0.46
     이후
    0.45
     Three
    0.44
     Handling
    0.43
     aspirants
    0.43
    candidates
    0.41
     Stick
    0.41
    Act Density 0.018%

    No Known Activations